Risk calls
92,888 decisions scored in 3 leagues · GNU Backgammon 1.08, 2-ply
Risk judgement all leagues · 95% interval · higher is better
No model of this kind on the leaderboard.
- OpenAI
- Anthropic
- DeepSeek
- xAI
- Meta
- Moonshot
- Liquid AI
- Base Labs
- Nace.AI
- Sthānika AI
- Alibaba
- Z.ai
- PelaAI
- REAX
- Fastino
- Turion.AI
- TypeSafe
- Perplexity
- Celeris
- Cloudflare
- StartLux
- Blockbrain Labs
- Subquadratic
- Apertix AI
- EldanRing
- Inception
- Zefan Cai
- OmniJev
- Knowledgator
- program
- 50 = always safe
| Counts 1, 2, 3 down the rows shown, by the measure chosen; no tiers. | The model and its setting. Tap or point at a name for its details. | 100 = every call right, 50 = always safe; higher is better. | 500 × mean 2-ply equity loss per decision, the checker-play performance rating (PR) backgammon players use; lower is better. | Dollars per 1,000 decisions at each setup's price basis (a list price, or API-equivalent for a subscription); not a bill paid. Lower is better. | Median request seconds per decision (waits between retries not included). Lower is better. |
|---|---|---|---|---|---|
| 1 | GPT-6 Astra high · chat · late entry Closed · FlagshipDetails | 74.471.8–77.0 (50 = always safe) | 8.8 | $59.356$59,356List price | 9.83 |
| GPT-6 Astra low · chat Closed · FlagshipDetails | 75.873.1–78.5 (50 = always safe) | 11.8 | $49.737$49,737List price | 3.94 | |
| GPT-6 Astra medium · chat Closed · FlagshipDetails | 74.771.9–77.3 (50 = always safe) | 11.1 | $50.268$50,268List price | 4.40 | |
| 2 | Gemini 4 Argon high · chat Closed · FlagshipDetails | 74.172.0–76.1 (50 = always safe) | 12.6 | $64.401$64,401List price | 27.5 |
| Gemini 4 Argon low · chat Closed · FlagshipDetails | 69.266.2–72.3 (50 = always safe) | 16.5 | $10.204$10,204List price | 3.82 | |
| 3 | Claude Fable 5.1 high · chat Closed · FlagshipDetails | 72.369.8–74.7 (50 = always safe) | 14.0 | $136.268$136,268List price | 12.7 |
| Claude Fable 5.1 low · chat Closed · FlagshipDetails | 67.865.6–69.9 (50 = always safe) | 17.9 | $62.613$62,613List price | 1.54 | |
| 4 | GPT-6.1 Sol high · chat Closed · WorkhorseDetails | 72.269.5–74.9 (50 = always safe) | 9.9 | $15.573$15,573List price | 13.1 |
| GPT-6.1 Sol low · chat Closed · WorkhorseDetails | 72.769.9–75.5 (50 = always safe) | 12.1 | $10.228$10,228List price | 4.33 | |
| 5 | Claude Opus 5.5 high · chat Closed · FlagshipDetails | 70.067.3–72.6 (50 = always safe) | 14.4 | $36.400$36,400List price | 6.35 |
| Claude Opus 5.5 low · chat Closed · FlagshipDetails | 66.964.7–69.2 (50 = always safe) | 15.4 | $29.062$29,062List price | 3.92 | |
| 6 | DeepSeek-V4.1-Flash low · API + NVIDIA RTX PRO 6000 Blackwell · first release · chat Open · 552B MoE · 16B activeDetails | 69.067.3–70.9 (50 = always safe) | 19.0 | $47.092$47,092GPU estimate | 43.8 |
| DeepSeek-V4.1-Flash low · API · 1017 · chat Open · 552B MoE · 16B activeDetails | 68.566.4–70.6 (50 = always safe) | 17.1 | $4.869$4,869List price | 22.3 | |
| DeepSeek-V4.1-Flash off · API + NVIDIA RTX PRO 6000 Blackwell · first release · chat Open · 552B MoE · 16B activeDetails | 59.357.1–61.5 (50 = always safe) | 35.6 | $0.728$728GPU estimate | 0.48 | |
| DeepSeek-V4.1-Flash off · API · 1017 · chat Open · 552B MoE · 16B activeDetails | 58.556.6–60.5 (50 = always safe) | 35.2 | $0.244$244List price | 0.84 | |
| 7 | Grok 4.7 high · chat Closed · WorkhorseDetails | 68.566.1–71.1 (50 = always safe) | 18.8 | $117.379$117,379List price | 122.3 |
| Grok 4.7 low · chat Closed · WorkhorseDetails | 67.766.0–69.5 (50 = always safe) | 19.1 | $32.813$32,813List price | 24.3 | |
| 8 | Claude Sonnet 5.5 high · chat Closed · WorkhorseDetails | 68.266.3–70.0 (50 = always safe) | 16.7 | $19.847$19,847List price | 6.63 |
| Claude Sonnet 5.5 low · chat Closed · WorkhorseDetails | 63.561.6–65.4 (50 = always safe) | 20.1 | $13.541$13,541List price | 1.51 | |
| 9 | Gemini 3.8 Flash high · chat Closed · WorkhorseDetails | 66.965.2–68.5 (50 = always safe) | 14.9 | $22.352$22,352List price | 9.59 |
| Gemini 3.8 Flash low · chat Closed · WorkhorseDetails | 65.163.5–66.8 (50 = always safe) | 16.3 | $4.123$4,123List price | 2.16 | |
| 10 | Muse Ember max · chat · late entry Closed · EfficientDetails | 66.063.9–68.2 (50 = always safe) | 20.1 | $6.863$6,863Billed | 15.3 |
| 11 | Kimi K3.1 Pro off · chat Open · 2.8T MoE · 104B activeDetails | 65.963.2–68.9 (50 = always safe) | 28.0 | $3.982$3,982List price | 2.11 |
| 12 | Gemini Decision 1 20261111 · decision · late entry Closed · EfficientDetails | 64.762.2–67.2 (50 = always safe) | 28.0 | $0.382$382Billed | 0.24 |
| 13 | Gemma 4 31B on · NVIDIA RTX PRO 6000 Blackwell + NVIDIA DGX Spark · chat Open · 31BDetails | 64.562.9–66.2 (50 = always safe) | 19.6 | $34.943$34,943GPU estimate | 120.6 |
| Gemma 4 31B off · NVIDIA RTX PRO 6000 Blackwell + NVIDIA DGX Spark · chat Open · 31BDetails | 62.660.4–65.0 (50 = always safe) | 22.5 | $8.215$8,215GPU estimate | 0.31 | |
| 14 | d1-ultra decision Closed · EfficientDetails | 64.061.7–66.3 (50 = always safe) | 30.3 | $0.145$145List price | 0.23 |
| 15 | Mammoth-1 NVIDIA RTX PRO 6000 Blackwell · decision · late entry Open · 27BDetails | 63.261.2–65.2 (50 = always safe) | 28.5 | $0.999$999GPU estimate | 0.72 |
| 16 | Drex Max NVIDIA RTX PRO 6000 Blackwell · decision · late entry Open · 27BDetails | 62.961.1–64.7 (50 = always safe) | 30.4 | $1.285$1,285GPU estimate | 0.68 |
| 17 | Sieve 31B v3 NVIDIA DGX Spark (GB10) · decision · late entry Open · 31BDetails | 62.760.6–64.9 (50 = always safe) | 27.5 | $0.794$794GPU estimate | 11.1 |
| 18 | Qwen3.8-27B low · NVIDIA RTX PRO 6000 Blackwell + NVIDIA DGX Spark · chat Open · 27BDetails | 62.060.1–63.9 (50 = always safe) | 29.0 | $39.023$39,023GPU estimate | 171.1 |
| Qwen3.8-27B off · NVIDIA RTX PRO 6000 Blackwell + NVIDIA DGX Spark · chat Open · 27BDetails | 57.656.1–59.0 (50 = always safe) | 45.0 | $4.551$4,551GPU estimate | 1.48 | |
| 19 | GLM-5.3 low · chat Open · 753B MoEDetails | 61.759.7–63.8 (50 = always safe) | 30.9 | $2.917$2,917List price | 1.75 |
| 20 | KnowLine-31B-Gen1.5 NVIDIA DGX Spark (GB10) · decision · late entry Open · 31BDetails | 61.659.6–63.5 (50 = always safe) | 26.2 | – | 3.45 |
| 21 | REAX 1.3 NVIDIA RTX PRO 6000 Blackwell · decision · late entry Open · 57BDetails | 60.558.7–62.4 (50 = always safe) | 27.8 | $1.545$1,545GPU estimate | 1.74 |
| 22 | GLiDE API · decision Closed · EfficientDetails | 60.458.3–62.6 (50 = always safe) | 33.2 | $0.153$153List price | 0.48 |
| 23 | Turion Jev 31B NVIDIA DGX Spark (GB10) · decision · late entry Open · 31BDetails | 59.657.7–61.4 (50 = always safe) | 29.7 | $0.293$293GPU estimate | 3.95 |
| 24 | Jev 1.13 decision Closed · EfficientDetails | 59.557.4–61.6 (50 = always safe) | 34.4 | $0.166$166List price | 0.22 |
| 25 | Qwen3.8 Flash off · chat Closed · EfficientDetails | 59.557.2–61.7 (50 = always safe) | 33.6 | $0.284$284List price | 1.70 |
| 26 | Jev 1.14 decision Closed · EfficientDetails | 59.357.1–61.4 (50 = always safe) | 31.7 | $0.173$173List price | 0.19 |
| 27 | Drex Max v1.1 decision · late entry Closed · Efficient (provisional)Details | 59.157.0–61.3 (50 = always safe) | 30.9 | $0.265$265List price | 0.44 |
| 28 | GLiDE v1.2 · NVIDIA RTX PRO 6000 Blackwell · decision Open · 27BDetails | 58.856.7–60.8 (50 = always safe) | 35.0 | $10.301$10,301GPU estimate | 1.41 |
| 29 | Drex 2.0 API · decision · late entry Open · 35B MoE · 3.0B activeDetails | 58.155.7–60.4 (50 = always safe) | 38.4 | $0.258$258Billed | 0.42 |
| Drex 2.0 NVIDIA RTX PRO 6000 Blackwell · decision · late entry Open · 35B MoE · 3.0B activeDetails | 53.050.5–55.2 (50 = always safe) | 42.9 | $0.782$782GPU estimate | 0.40 | |
| 30 | Perplexity Decider 27B v1.2 NVIDIA RTX PRO 6000 Blackwell · decision Open · 27BDetails | 57.956.0–59.9 (50 = always safe) | 36.9 | $12.227$12,227GPU estimate | 0.94 |
| 31 | celeris-1-decision decision Closed · EfficientDetails | 57.855.9–59.7 (50 = always safe) | 35.6 | $0.150$150List price | 0.17 |
| 32 | Elephant-1 NVIDIA RTX PRO 6000 Blackwell · decision · late entry Open · 9.0BDetails | 57.755.8–59.6 (50 = always safe) | 44.6 | $0.685$685GPU estimate | 0.26 |
| 33 | Clef NVIDIA RTX PRO 6000 Blackwell + NVIDIA DGX Spark · decision Open · 27BDetails | 57.555.4–59.8 (50 = always safe) | 36.5 | $5.736$5,736GPU estimate | 1.13 |
| 34 | StartLux-Decision-v1.1-4B-Instant NVIDIA DGX Spark (GB10) · decision · late entry Open · 4.0BDetails | 57.255.0–59.3 (50 = always safe) | 40.1 | $0.072$71.58GPU estimate | 0.44 |
| 35 | Cygnet NVIDIA RTX PRO 6000 Blackwell + NVIDIA DGX Spark · decision Open · 12BDetails | 57.155.3–58.8 (50 = always safe) | 38.6 | $11.168$11,168GPU estimate | 0.37 |
| 36 | Perplexity Decider 27B v1.1 NVIDIA RTX PRO 6000 Blackwell + NVIDIA DGX Spark · decision Open · 27BDetails | 56.954.9–58.8 (50 = always safe) | 38.8 | $6.593$6,593GPU estimate | 1.97 |
| 37 | SubQ Snap 1.1 decision · late entry Closed · EfficientDetails | 56.754.8–58.6 (50 = always safe) | 40.2 | $0.150$150Billed | 0.23 |
| 38 | SubQ Snap Preview decision Closed · EfficientDetails | 56.553.8–59.1 (50 = always safe) | 43.9 | $0.193$193List price | 0.24 |
| 39 | Cerno 9B v1.2 NVIDIA DGX Spark (GB10) · decision · late entry Open · 9.0BDetails | 56.153.9–58.2 (50 = always safe) | 48.5 | $0.139$139GPU estimate | 1.96 |
| 40 | GPT-6 Luna Decisions API · decision Closed · EfficientDetails | 55.753.8–57.6 (50 = always safe) | 43.3 | $0.335$335List price | 0.23 |
| 41 | d1-2B NVIDIA RTX PRO 6000 Blackwell · decision · late entry Open · 1.9BDetails | 55.252.8–57.5 (50 = always safe) | 47.1 | $0.467$467GPU estimate | 0.06 |
| 42 | Winnow-12B NVIDIA RTX PRO 6000 Blackwell · decision Open · 12BDetails | 55.252.9–57.2 (50 = always safe) | 49.7 | $9.615$9,615GPU estimate | 2.46 |
| 43 | StartLux-Decision-v1.1-2B-Instant NVIDIA DGX Spark (GB10) · decision · late entry Open · 2.0BDetails | 53.851.3–56.6 (50 = always safe) | 50.0 | $0.052$52.30GPU estimate | 0.21 |
| 44 | Mercury Decide decision Closed · EfficientDetails | 53.451.5–55.2 (50 = always safe) | 47.9 | $0.071$71.34List price | 0.48 |
| 45 | d1-Omni-2B NVIDIA RTX PRO 6000 Blackwell · decision · late entry Open · 2.2BDetails | 53.250.9–55.6 (50 = always safe) | 49.8 | $0.657$657GPU estimate | 0.06 |
| 46 | LFM2.5-24B-A2B on · NVIDIA RTX PRO 6000 Blackwell + NVIDIA DGX Spark · chat Open · 24B MoE · 2.5B activeDetails | 52.450.3–54.5 (50 = always safe) | 47.7 | $38.716$38,716GPU estimate | 324.8 |
| LFM2.5-24B-A2B off · NVIDIA RTX PRO 6000 Blackwell · chat Open · 24B MoE · 2.5B activeDetails | 45.743.2–48.1 (50 = always safe) | 61.5 | $9.132$9,132GPU estimate | 0.14 | |
| 47 | KnowLine-2B-Gen1 NVIDIA DGX Spark (GB10) · decision · late entry Open · 2.0BDetails | 51.148.7–53.5 (50 = always safe) | 54.5 | $0.049$49.34GPU estimate | 0.15 |
| 48 | KnowLine 4B Gen5.5 NVIDIA DGX Spark (GB10) · decision · late entry Open · 4.0BDetails | 49.747.0–52.3 (50 = always safe) | 53.6 | $0.054$53.72GPU estimate | 0.28 |
| 49 | Perplexity Decider Flash v1.2 NVIDIA RTX PRO 6000 Blackwell · decision Open · 4.0BDetails | 49.146.5–51.6 (50 = always safe) | 59.6 | $12.267$12,267GPU estimate | 0.56 |
| 50 | Open-Jev-27B-v1.1 NVIDIA RTX PRO 6000 Blackwell · decision Open · 27BDetails | 48.546.1–50.9 (50 = always safe) | 65.6 | $7.185$7,185GPU estimate | 1.57 |
| 51 | GLiDE 2B NVIDIA DGX Spark (GB10) · decision · late entry Open · 1.9BDetails | 46.743.6–49.6 (50 = always safe) | 67.4 | $0.058$58.31GPU estimate | 0.33 |
| 52 | KnowLine-0.8B-Gen1 NVIDIA DGX Spark (GB10) · decision · late entry Open · 0.8BDetails | 45.242.5–47.7 (50 = always safe) | 71.9 | $0.049$48.93GPU estimate | 0.11 |
| 53 | StartLux-Decision-v1.1-0.8B-Instant NVIDIA DGX Spark (GB10) · decision · late entry Open · 0.8BDetails | 44.642.3–46.9 (50 = always safe) | 64.7 | $0.054$53.72GPU estimate | 0.13 |
| 54 | OneJev1.6-0.8B NVIDIA DGX Spark (GB10) · decision · late entry Open · 0.9BDetails | 42.539.3–45.8 (50 = always safe) | 82.5 | $0.052$51.90GPU estimate | 0.10 |
| 55 | GLiDE 0.8B NVIDIA DGX Spark (GB10) · decision · late entry Open · 0.8BDetails | 41.738.9–44.3 (50 = always safe) | 80.4 | $0.051$51.47GPU estimate | 0.22 |
| 56 | GLiDE 0.4B NVIDIA DGX Spark (GB10) · decision · late entry Open · 0.4BDetails | 28.925.6–32.1 (50 = always safe) | 113.2 | $0.057$57.11GPU estimate | 0.13 |
| 57 | GLiClass v4 Edge NVIDIA DGX Spark (GB10) · decision · late entry Open · 0.4BDetails | 21.518.6–24.6 (50 = always safe) | 133.5 | $0.174$174GPU estimate | 1.33 |
| GNUbg weak programDetails | 67.163.8–70.3 (50 = always safe) | 21.4 | – | 0.01 | |
| GNUbg weak programDetails | 62.359.5–64.8 (50 = always safe) | 27.0 | – | 0.01 | |
| GNUbg weak programDetails | 62.158.2–65.9 (50 = always safe) | 28.1 | – | 0.01 | |
| Safest programDetails | 50.050.0–50.0 (50 = always safe) | 51.6 | – | 0.00 | |
| Safest (computed) programDetails | 50.050.0–50.0 (50 = always safe) | – | – | Not measured | |
| Safest (computed) programDetails | 50.050.0–50.0 (50 = always safe) | – | – | Not measured | |
| Random programDetails | 24.922.3–27.4 (50 = always safe) | 121.1 | – | 0.00 | |
| Random (computed) programDetails | 27.026.7–27.2 (50 = always safe) | – | – | Not measured | |
| Random (computed) programDetails | 27.627.1–28.0 (50 = always safe) | – | – | Not measured |
No model of this kind on the leaderboard.
Risk judgement: 100 = every call right, 50 = always safe; higher is better. One row per model at its highest reasoning setting, never its best score; late entries included. All setups: every setup of every model. How rows are chosen
Leagues played different positions; close scores across leagues need not mean a real difference. *
Rank counts 1, 2, 3 down the rows shown, by the measure shown (with a filter on, among those rows only); it has no tiers: a tier needs a paired test (McNemar, Holm) over positions every model answered, and each league played its own positions, so models in different leagues never answered the same ones. The tier in each row's details and Same positions (preview) come from 200 positions every model there answered. Rank comes from league play; tier comes from the same 200 positions for every model. Ranks show observed scores; small gaps need not be meaningful.
$ per 1,000 decisions: At each setup's price basis (a list price, or API-equivalent for a subscription); not a bill paid. Each cost's tag opens how it was counted; each row's details name its price basis.
Class: by the maker's total parameters, or by list price when the size is undisclosed *
Size by total parameters, as disclosed by the maker (for MoE models the label also shows active parameters): Tiny under 6B · Small 6B–15B · Medium over 15B up to 40B · Large over 40B. Models of undisclosed size, by standard list price per 1M input tokens: Efficient up to $0.50 · Workhorse up to $3 · Flagship over $3.
Learning Ordered: Yes, then No, then not finished; each by the change in risks found. Not a ranking.
| The setup tested: the model and its setting. Tap or point at a name for its details. | Yes: the change in risks found is above the threshold and right safety falls by no more than 5 pp. No: either fails. Shown once every run is complete; before that, the model's state (running, queued, waiting and why, not tested and the rule). | Risks found after the series minus before, in percentage points (pp): points of the share, not a relative percent. | Took the risk when it paid, as a share of the positions where it did: before = the mean of its 3 empty runs (no lessons), after = after the series of lessons. | Right safety (played safe when safe was right) after minus before, in percentage points. A fall of more than 5 pp makes the result No. | What the change must beat: the larger of the model's own spread over its 3 empty runs (max − min of risks found) and 5 pp. | |
|---|---|---|---|---|---|---|
| Improved: Yes | ||||||
| – | GLM-5.3 low · chat Open · 753B MoEDetails | Yes | +17.6 | 21.3 → 39.0 | −4.0 | 9.0 |
| – | Claude Fable 5.1 high · chat Closed · FlagshipDetails | Yes | +9.4 | 54.0 → 63.4 | −2.1 | 5.0 |
| Claude Fable 5.1 low · chat Closed · FlagshipDetails | not in the learning plan | |||||
| – | Gemini 4 Argon high · chat Closed · FlagshipDetails | Yes | +8.5Run 2 | 53.3 → 61.8 | −1.5 | 5.0 |
| Gemini 4 Argon low · chat Closed · FlagshipDetails | not in the learning plan | |||||
| – | Gemma 4 31B on · NVIDIA RTX PRO 6000 Blackwell + NVIDIA DGX Spark · chat Open · 31BDetails | Yes | +8.5 | 34.3 → 42.8 | −1.7 | 5.0 |
| Gemma 4 31B off · NVIDIA RTX PRO 6000 Blackwell + NVIDIA DGX Spark · chat Open · 31BDetails | not in the learning plan | |||||
| – | DeepSeek-V4.1-Flash low · API + NVIDIA RTX PRO 6000 Blackwell · first release · chat Open · 552B MoE · 16B activeDetails | Yes | +8.2Run 2 | 44.6 → 52.9 | −3.6 | 5.0 |
| DeepSeek-V4.1-Flash low · API · 1017 · chat Open · 552B MoE · 16B activeDetails | not in the learning plan | |||||
| DeepSeek-V4.1-Flash off · API + NVIDIA RTX PRO 6000 Blackwell · first release · chat Open · 552B MoE · 16B activeDetails | not in the learning plan | |||||
| DeepSeek-V4.1-Flash off · API · 1017 · chat Open · 552B MoE · 16B activeDetails | not in the learning plan | |||||
| – | Gemini 3.8 Flash high · chat Closed · WorkhorseDetails | Yes | +8.2 | 38.0 → 46.2 | −1.9 | 5.0 |
| Gemini 3.8 Flash low · chat Closed · WorkhorseDetails | not in the learning plan | |||||
| – | Claude Sonnet 5.5 high · chat Closed · WorkhorseDetails | Yes | +7.0 | 43.0 → 50.0 | −2.9 | 5.0 |
| Claude Sonnet 5.5 low · chat Closed · WorkhorseDetails | not in the learning plan | |||||
| – | Claude Opus 5.5 high · chat Closed · FlagshipDetails | Yes | +6.7 | 47.3 → 54.0 | +1.1 | 5.0 |
| Claude Opus 5.5 low · chat Closed · FlagshipDetails | not in the learning plan | |||||
| Improved: No | ||||||
| – | Qwen3.8-27B low · NVIDIA RTX PRO 6000 Blackwell + NVIDIA DGX Spark · chat Open · 27BDetails | Noright safety fell past the limit | +19.0 | 32.0 → 51.0 | −7.1past the −5 limit | 5.0 |
| Qwen3.8-27B off · NVIDIA RTX PRO 6000 Blackwell + NVIDIA DGX Spark · chat Open · 27BDetails | not in the learning plan | |||||
| – | Kimi K3.1 Pro off · chat Open · 2.8T MoE · 104B activeDetails | No | +4.8 | 41.0 → 45.8 | +1.2 | 5.0 |
| – | Qwen3.8 Flash off · chat Closed · EfficientDetails | No | +2.7 | 33.3 → 36.0 | +1.5 | 5.0 |
| Not finished | ||||||
| – | GPT-6 Astra high · chat · late entry Closed · FlagshipDetails | pending | N/A | N/A → N/A | N/A | N/A |
| GPT-6 Astra low · chat Closed · FlagshipDetails | not in the learning plan | |||||
| GPT-6 Astra medium · chat Closed · FlagshipDetails | not in the learning plan | |||||
| – | GPT-6.1 Sol high · chat Closed · WorkhorseDetails | pending · numbers interim | +5.2 | 59.3 → 64.5 | +2.7 | 8.0 |
| GPT-6.1 Sol low · chat Closed · WorkhorseDetails | not in the learning plan | |||||
| – | Grok 4.7 high · chat Closed · WorkhorseDetails | pending · numbers interim | +8.2 | 48.5 → 56.7 | −5.2past the −5 limit | N/A |
| Grok 4.7 low · chat Closed · WorkhorseDetails | not in the learning plan | |||||
| – | d1-ultra decision Closed · EfficientDetails | not tested (conservative context guard) | ||||
| – | Mammoth-1 NVIDIA RTX PRO 6000 Blackwell · decision · late entry Open · 27BDetails | waiting (Ümit's D5 decision) | ||||
| – | REAX 1.3 NVIDIA RTX PRO 6000 Blackwell · decision · late entry Open · 57BDetails | waiting (Ümit's D5 decision) | ||||
| – | Jev 1.14 decision Closed · EfficientDetails | not tested (conservative context guard) | ||||
| – | Drex Max v1.1 decision · late entry Closed · Efficient (provisional)Details | notes: complete · worst: waiting (cash approval) | ||||
| – | GLiDE v1.2 · NVIDIA RTX PRO 6000 Blackwell · decision Open · 27BDetails | notes: stopped (its budget cap was reached) · worst: complete | ||||
| – | Perplexity Decider 27B v1.2 NVIDIA RTX PRO 6000 Blackwell · decision Open · 27BDetails | complete | ||||
| – | Elephant-1 NVIDIA RTX PRO 6000 Blackwell · decision · late entry Open · 9.0BDetails | notes: waiting (Ümit's D5 decision) · worst: complete | ||||
| – | Cygnet NVIDIA RTX PRO 6000 Blackwell + NVIDIA DGX Spark · decision Open · 12BDetails | waiting (its layer never sees the lessons) | ||||
| – | SubQ Snap 1.1 decision · late entry Closed · EfficientDetails | complete | ||||
| – | d1-2B NVIDIA RTX PRO 6000 Blackwell · decision · late entry Open · 1.9BDetails | not started (no backgammon route yet; no league record) | ||||
| – | Winnow-12B NVIDIA RTX PRO 6000 Blackwell · decision Open · 12BDetails | notes: waiting (cash approval) · worst: waiting (its render check) | ||||
| – | StartLux-Decision-v1.1-2B-Instant NVIDIA DGX Spark (GB10) · decision · late entry Open · 2.0BDetails | notes: waiting (cash approval) · worst: waiting (its render check) | ||||
| – | LFM2.5-24B-A2B on · NVIDIA RTX PRO 6000 Blackwell + NVIDIA DGX Spark · chat Open · 24B MoE · 2.5B activeDetails | pending · numbers interim | −8.4 | 29.7 → 21.2 | +0.3 | 11.0 |
| LFM2.5-24B-A2B off · NVIDIA RTX PRO 6000 Blackwell · chat Open · 24B MoE · 2.5B activeDetails | not in the learning plan | |||||
| – | KnowLine-2B-Gen1 NVIDIA DGX Spark (GB10) · decision · late entry Open · 2.0BDetails | notes: waiting (cash approval) · worst: waiting (its render check) | ||||
| – | KnowLine 4B Gen5.5 NVIDIA DGX Spark (GB10) · decision · late entry Open · 4.0BDetails | notes: waiting (cash approval) · worst: waiting (its render check) | ||||
| – | Perplexity Decider Flash v1.2 NVIDIA RTX PRO 6000 Blackwell · decision Open · 4.0BDetails | notes: waiting (cash approval) · worst: waiting (its render check) | ||||
| – | GLiDE 2B NVIDIA DGX Spark (GB10) · decision · late entry Open · 1.9BDetails | notes: waiting (cash approval) · worst: waiting (its render check) | ||||
| – | KnowLine-0.8B-Gen1 NVIDIA DGX Spark (GB10) · decision · late entry Open · 0.8BDetails | notes: waiting (cash approval) · worst: waiting (its render check) | ||||
| – | StartLux-Decision-v1.1-0.8B-Instant NVIDIA DGX Spark (GB10) · decision · late entry Open · 0.8BDetails | notes: waiting (cash approval) · worst: waiting (its render check) | ||||
| – | OneJev1.6-0.8B NVIDIA DGX Spark (GB10) · decision · late entry Open · 0.9BDetails | notes: waiting (cash approval) · worst: waiting (its render check) | ||||
| – | GLiDE 0.8B NVIDIA DGX Spark (GB10) · decision · late entry Open · 0.8BDetails | notes: waiting (cash approval) · worst: waiting (its render check) | ||||
| – | GLiDE 0.4B NVIDIA DGX Spark (GB10) · decision · late entry Open · 0.4BDetails | notes: waiting (cash approval) · worst: waiting (its render check) | ||||
| – | GLiClass v4 Edge NVIDIA DGX Spark (GB10) · decision · late entry Open · 0.4BDetails | notes: waiting (cash approval) · worst: waiting (its render check) | ||||
| Not in the learning plan | ||||||
| – | Muse Ember max · chat · late entry Closed · EfficientDetails | not in the learning plan | ||||
| – | Gemini Decision 1 20261111 · decision · late entry Closed · EfficientDetails | not in the learning plan | ||||
| – | Drex Max NVIDIA RTX PRO 6000 Blackwell · decision · late entry Open · 27BDetails | not in the learning plan | ||||
| – | Sieve 31B v3 NVIDIA DGX Spark (GB10) · decision · late entry Open · 31BDetails | not in the learning plan | ||||
| – | KnowLine-31B-Gen1.5 NVIDIA DGX Spark (GB10) · decision · late entry Open · 31BDetails | not in the learning plan | ||||
| – | GLiDE API · decision Closed · EfficientDetails | not in the learning plan | ||||
| – | Turion Jev 31B NVIDIA DGX Spark (GB10) · decision · late entry Open · 31BDetails | not in the learning plan | ||||
| – | Jev 1.13 decision Closed · EfficientDetails | not in the learning plan | ||||
| – | Drex 2.0 API · decision · late entry Open · 35B MoE · 3.0B activeDetails | not in the learning plan | ||||
| Drex 2.0 NVIDIA RTX PRO 6000 Blackwell · decision · late entry Open · 35B MoE · 3.0B activeDetails | not in the learning plan | |||||
| – | celeris-1-decision decision Closed · EfficientDetails | not in the learning plan | ||||
| – | Clef NVIDIA RTX PRO 6000 Blackwell + NVIDIA DGX Spark · decision Open · 27BDetails | not in the learning plan | ||||
| – | StartLux-Decision-v1.1-4B-Instant NVIDIA DGX Spark (GB10) · decision · late entry Open · 4.0BDetails | not in the learning plan | ||||
| – | Perplexity Decider 27B v1.1 NVIDIA RTX PRO 6000 Blackwell + NVIDIA DGX Spark · decision Open · 27BDetails | not in the learning plan | ||||
| – | SubQ Snap Preview decision Closed · EfficientDetails | not in the learning plan | ||||
| – | Cerno 9B v1.2 NVIDIA DGX Spark (GB10) · decision · late entry Open · 9.0BDetails | not in the learning plan | ||||
| – | GPT-6 Luna Decisions API · decision Closed · EfficientDetails | not in the learning plan | ||||
| – | Mercury Decide decision Closed · EfficientDetails | not in the learning plan | ||||
| – | d1-Omni-2B NVIDIA RTX PRO 6000 Blackwell · decision · late entry Open · 2.2BDetails | not in the learning plan | ||||
| – | Open-Jev-27B-v1.1 NVIDIA RTX PRO 6000 Blackwell · decision Open · 27BDetails | not in the learning plan | ||||
| GNUbg weak programDetails | program · not in the learning plan | |||||
| GNUbg weak programDetails | program · not in the learning plan | |||||
| GNUbg weak programDetails | program · not in the learning plan | |||||
| Safest programDetails | program · not in the learning plan | |||||
| Safest (computed) programDetails | program · not in the learning plan | |||||
| Safest (computed) programDetails | program · not in the learning plan | |||||
| Random programDetails | program · not in the learning plan | |||||
| Random (computed) programDetails | program · not in the learning plan | |||||
| Random (computed) programDetails | program · not in the learning plan | |||||
No model of this kind on the leaderboard.
Every model on the leaderboard: its verdict after lessons where one is published (Run 2 where it replaced the original), else its state in the learning lanes, as their status files give it. Did they improve?
Result: Yes or No once every run is complete; the change, right safety change and threshold are in points (pp). *
Threshold: the larger of the model's own spread over its three empty runs (max − min) and 5 points; right safety may fall by at most 5 points.
Class: by the maker's total parameters, or by list price when the size is undisclosed *
Size by total parameters, as disclosed by the maker (for MoE models the label also shows active parameters): Tiny under 6B · Small 6B–15B · Medium over 15B up to 40B · Large over 40B. Models of undisclosed size, by standard list price per 1M input tokens: Efficient up to $0.50 · Workhorse up to $3 · Flagship over $3.
Error rate (PR) all leagues · 95% interval · lower is better
No model of this kind on the leaderboard.
- OpenAI
- Anthropic
- xAI
- DeepSeek
- Meta
- PelaAI
- Sthānika AI
- REAX
- Moonshot
- Base Labs
- Alibaba
- Turion.AI
- Liquid AI
- Nace.AI
- Z.ai
- TypeSafe
- Fastino
- Celeris
- Cloudflare
- Perplexity
- Blockbrain Labs
- StartLux
- Subquadratic
- Inception
- Apertix AI
- EldanRing
- Zefan Cai
- OmniJev
- Knowledgator
- program
| Counts 1, 2, 3 down the rows shown, by the measure chosen; no tiers. | The model and its setting. Tap or point at a name for its details. | 500 × mean 2-ply equity loss per decision, the checker-play performance rating (PR) backgammon players use; lower is better. | 100 = every call right, 50 = always safe; higher is better. | Dollars per 1,000 decisions at each setup's price basis (a list price, or API-equivalent for a subscription); not a bill paid. Lower is better. | Median request seconds per decision (waits between retries not included). Lower is better. |
|---|---|---|---|---|---|
| 1 | GPT-6 Astra high · chat · late entry Closed · FlagshipDetails | 8.87.4–10.3 | 74.4 | $59.356$59,356List price | 9.83 |
| GPT-6 Astra medium · chat Closed · FlagshipDetails | 11.19.5–12.9 | 74.7 | $50.268$50,268List price | 4.40 | |
| GPT-6 Astra low · chat Closed · FlagshipDetails | 11.89.5–14.2 | 75.8 | $49.737$49,737List price | 3.94 | |
| 2 | GPT-6.1 Sol high · chat Closed · WorkhorseDetails | 9.98.6–11.3 | 72.2 | $15.573$15,573List price | 13.1 |
| GPT-6.1 Sol low · chat Closed · WorkhorseDetails | 12.110.5–13.7 | 72.7 | $10.228$10,228List price | 4.33 | |
| 3 | Gemini 4 Argon high · chat Closed · FlagshipDetails | 12.610.5–14.8 | 74.1 | $64.401$64,401List price | 27.5 |
| Gemini 4 Argon low · chat Closed · FlagshipDetails | 16.513.7–19.5 | 69.2 | $10.204$10,204List price | 3.82 | |
| 4 | Claude Fable 5.1 high · chat Closed · FlagshipDetails | 14.011.5–16.3 | 72.3 | $136.268$136,268List price | 12.7 |
| Claude Fable 5.1 low · chat Closed · FlagshipDetails | 17.915.9–20.1 | 67.8 | $62.613$62,613List price | 1.54 | |
| 5 | Claude Opus 5.5 high · chat Closed · FlagshipDetails | 14.412.1–17.0 | 70.0 | $36.400$36,400List price | 6.35 |
| Claude Opus 5.5 low · chat Closed · FlagshipDetails | 15.413.1–18.0 | 66.9 | $29.062$29,062List price | 3.92 | |
| 6 | Gemini 3.8 Flash high · chat Closed · WorkhorseDetails | 14.912.9–17.0 | 66.9 | $22.352$22,352List price | 9.59 |
| Gemini 3.8 Flash low · chat Closed · WorkhorseDetails | 16.314.5–18.2 | 65.1 | $4.123$4,123List price | 2.16 | |
| 7 | Claude Sonnet 5.5 high · chat Closed · WorkhorseDetails | 16.714.9–18.7 | 68.2 | $19.847$19,847List price | 6.63 |
| Claude Sonnet 5.5 low · chat Closed · WorkhorseDetails | 20.117.8–22.4 | 63.5 | $13.541$13,541List price | 1.51 | |
| 8 | Grok 4.7 high · chat Closed · WorkhorseDetails | 18.815.9–21.8 | 68.5 | $117.379$117,379List price | 122.3 |
| Grok 4.7 low · chat Closed · WorkhorseDetails | 19.116.9–21.4 | 67.7 | $32.813$32,813List price | 24.3 | |
| 9 | DeepSeek-V4.1-Flash low · API + NVIDIA RTX PRO 6000 Blackwell · first release · chat Open · 552B MoE · 16B activeDetails | 19.016.6–21.3 | 69.0 | $47.092$47,092GPU estimate | 43.8 |
| DeepSeek-V4.1-Flash low · API · 1017 · chat Open · 552B MoE · 16B activeDetails | 17.115.1–19.2 | 68.5 | $4.869$4,869List price | 22.3 | |
| DeepSeek-V4.1-Flash off · API · 1017 · chat Open · 552B MoE · 16B activeDetails | 35.231.8–38.8 | 58.5 | $0.244$244List price | 0.84 | |
| DeepSeek-V4.1-Flash off · API + NVIDIA RTX PRO 6000 Blackwell · first release · chat Open · 552B MoE · 16B activeDetails | 35.631.7–39.7 | 59.3 | $0.728$728GPU estimate | 0.48 | |
| 10 | Gemma 4 31B on · NVIDIA RTX PRO 6000 Blackwell + NVIDIA DGX Spark · chat Open · 31BDetails | 19.617.5–21.7 | 64.5 | $34.943$34,943GPU estimate | 120.6 |
| Gemma 4 31B off · NVIDIA RTX PRO 6000 Blackwell + NVIDIA DGX Spark · chat Open · 31BDetails | 22.519.9–25.3 | 62.6 | $8.215$8,215GPU estimate | 0.31 | |
| 11 | Muse Ember max · chat · late entry Closed · EfficientDetails | 20.117.6–22.7 | 66.0 | $6.863$6,863Billed | 15.3 |
| 12 | KnowLine-31B-Gen1.5 NVIDIA DGX Spark (GB10) · decision · late entry Open · 31BDetails | 26.223.0–29.4 | 61.6 | – | 3.45 |
| 13 | Sieve 31B v3 NVIDIA DGX Spark (GB10) · decision · late entry Open · 31BDetails | 27.524.1–31.6 | 62.7 | $0.794$794GPU estimate | 11.1 |
| 14 | REAX 1.3 NVIDIA RTX PRO 6000 Blackwell · decision · late entry Open · 57BDetails | 27.824.9–30.6 | 60.5 | $1.545$1,545GPU estimate | 1.74 |
| 15 | Gemini Decision 1 20261111 · decision · late entry Closed · EfficientDetails | 28.025.0–31.1 | 64.7 | $0.382$382Billed | 0.24 |
| 16 | Kimi K3.1 Pro off · chat Open · 2.8T MoE · 104B activeDetails | 28.024.5–31.8 | 65.9 | $3.982$3,982List price | 2.11 |
| 17 | Mammoth-1 NVIDIA RTX PRO 6000 Blackwell · decision · late entry Open · 27BDetails | 28.526.2–31.1 | 63.2 | $0.999$999GPU estimate | 0.72 |
| 18 | Qwen3.8-27B low · NVIDIA RTX PRO 6000 Blackwell + NVIDIA DGX Spark · chat Open · 27BDetails | 29.026.5–31.8 | 62.0 | $39.023$39,023GPU estimate | 171.1 |
| Qwen3.8-27B off · NVIDIA RTX PRO 6000 Blackwell + NVIDIA DGX Spark · chat Open · 27BDetails | 45.040.7–49.9 | 57.6 | $4.551$4,551GPU estimate | 1.48 | |
| 19 | Turion Jev 31B NVIDIA DGX Spark (GB10) · decision · late entry Open · 31BDetails | 29.726.5–33.3 | 59.6 | $0.293$293GPU estimate | 3.95 |
| 20 | d1-ultra decision Closed · EfficientDetails | 30.327.3–33.4 | 64.0 | $0.145$145List price | 0.23 |
| 21 | Drex Max NVIDIA RTX PRO 6000 Blackwell · decision · late entry Open · 27BDetails | 30.427.4–33.4 | 62.9 | $1.285$1,285GPU estimate | 0.68 |
| 22 | GLM-5.3 low · chat Open · 753B MoEDetails | 30.927.8–34.0 | 61.7 | $2.917$2,917List price | 1.75 |
| 23 | Drex Max v1.1 decision · late entry Closed · Efficient (provisional)Details | 30.928.2–33.7 | 59.1 | $0.265$265List price | 0.44 |
| 24 | Jev 1.14 decision Closed · EfficientDetails | 31.728.3–35.7 | 59.3 | $0.173$173List price | 0.19 |
| 25 | GLiDE API · decision Closed · EfficientDetails | 33.230.2–36.4 | 60.4 | $0.153$153List price | 0.48 |
| 26 | Qwen3.8 Flash off · chat Closed · EfficientDetails | 33.630.8–36.7 | 59.5 | $0.284$284List price | 1.70 |
| 27 | Jev 1.13 decision Closed · EfficientDetails | 34.431.0–38.0 | 59.5 | $0.166$166List price | 0.22 |
| 28 | GLiDE v1.2 · NVIDIA RTX PRO 6000 Blackwell · decision Open · 27BDetails | 35.031.6–39.0 | 58.8 | $10.301$10,301GPU estimate | 1.41 |
| 29 | celeris-1-decision decision Closed · EfficientDetails | 35.632.0–39.4 | 57.8 | $0.150$150List price | 0.17 |
| 30 | Clef NVIDIA RTX PRO 6000 Blackwell + NVIDIA DGX Spark · decision Open · 27BDetails | 36.533.5–39.6 | 57.5 | $5.736$5,736GPU estimate | 1.13 |
| 31 | Perplexity Decider 27B v1.2 NVIDIA RTX PRO 6000 Blackwell · decision Open · 27BDetails | 36.933.9–40.1 | 57.9 | $12.227$12,227GPU estimate | 0.94 |
| 32 | Drex 2.0 API · decision · late entry Open · 35B MoE · 3.0B activeDetails | 38.435.6–41.4 | 58.1 | $0.258$258Billed | 0.42 |
| Drex 2.0 NVIDIA RTX PRO 6000 Blackwell · decision · late entry Open · 35B MoE · 3.0B activeDetails | 42.939.1–47.1 | 53.0 | $0.782$782GPU estimate | 0.40 | |
| 33 | Cygnet NVIDIA RTX PRO 6000 Blackwell + NVIDIA DGX Spark · decision Open · 12BDetails | 38.635.4–41.9 | 57.1 | $11.168$11,168GPU estimate | 0.37 |
| 34 | Perplexity Decider 27B v1.1 NVIDIA RTX PRO 6000 Blackwell + NVIDIA DGX Spark · decision Open · 27BDetails | 38.835.3–42.5 | 56.9 | $6.593$6,593GPU estimate | 1.97 |
| 35 | StartLux-Decision-v1.1-4B-Instant NVIDIA DGX Spark (GB10) · decision · late entry Open · 4.0BDetails | 40.136.7–43.7 | 57.2 | $0.072$71.58GPU estimate | 0.44 |
| 36 | SubQ Snap 1.1 decision · late entry Closed · EfficientDetails | 40.236.7–43.8 | 56.7 | $0.150$150Billed | 0.23 |
| 37 | GPT-6 Luna Decisions API · decision Closed · EfficientDetails | 43.339.7–46.9 | 55.7 | $0.335$335List price | 0.23 |
| 38 | SubQ Snap Preview decision Closed · EfficientDetails | 43.939.3–48.8 | 56.5 | $0.193$193List price | 0.24 |
| 39 | Elephant-1 NVIDIA RTX PRO 6000 Blackwell · decision · late entry Open · 9.0BDetails | 44.640.3–48.9 | 57.7 | $0.685$685GPU estimate | 0.26 |
| 40 | d1-2B NVIDIA RTX PRO 6000 Blackwell · decision · late entry Open · 1.9BDetails | 47.142.8–51.5 | 55.2 | $0.467$467GPU estimate | 0.06 |
| 41 | LFM2.5-24B-A2B on · NVIDIA RTX PRO 6000 Blackwell + NVIDIA DGX Spark · chat Open · 24B MoE · 2.5B activeDetails | 47.744.1–51.2 | 52.4 | $38.716$38,716GPU estimate | 324.8 |
| LFM2.5-24B-A2B off · NVIDIA RTX PRO 6000 Blackwell · chat Open · 24B MoE · 2.5B activeDetails | 61.556.3–66.8 | 45.7 | $9.132$9,132GPU estimate | 0.14 | |
| 42 | Mercury Decide decision Closed · EfficientDetails | 47.943.3–52.9 | 53.4 | $0.071$71.34List price | 0.48 |
| 43 | Cerno 9B v1.2 NVIDIA DGX Spark (GB10) · decision · late entry Open · 9.0BDetails | 48.544.5–52.6 | 56.1 | $0.139$139GPU estimate | 1.96 |
| 44 | Winnow-12B NVIDIA RTX PRO 6000 Blackwell · decision Open · 12BDetails | 49.745.9–53.6 | 55.2 | $9.615$9,615GPU estimate | 2.46 |
| 45 | d1-Omni-2B NVIDIA RTX PRO 6000 Blackwell · decision · late entry Open · 2.2BDetails | 49.843.5–57.4 | 53.2 | $0.657$657GPU estimate | 0.06 |
| 46 | StartLux-Decision-v1.1-2B-Instant NVIDIA DGX Spark (GB10) · decision · late entry Open · 2.0BDetails | 50.045.4–54.8 | 53.8 | $0.052$52.30GPU estimate | 0.21 |
| 47 | KnowLine 4B Gen5.5 NVIDIA DGX Spark (GB10) · decision · late entry Open · 4.0BDetails | 53.648.8–58.6 | 49.7 | $0.054$53.72GPU estimate | 0.28 |
| 48 | KnowLine-2B-Gen1 NVIDIA DGX Spark (GB10) · decision · late entry Open · 2.0BDetails | 54.548.9–60.8 | 51.1 | $0.049$49.34GPU estimate | 0.15 |
| 49 | Perplexity Decider Flash v1.2 NVIDIA RTX PRO 6000 Blackwell · decision Open · 4.0BDetails | 59.654.9–64.5 | 49.1 | $12.267$12,267GPU estimate | 0.56 |
| 50 | StartLux-Decision-v1.1-0.8B-Instant NVIDIA DGX Spark (GB10) · decision · late entry Open · 0.8BDetails | 64.759.3–70.3 | 44.6 | $0.054$53.72GPU estimate | 0.13 |
| 51 | Open-Jev-27B-v1.1 NVIDIA RTX PRO 6000 Blackwell · decision Open · 27BDetails | 65.659.7–71.9 | 48.5 | $7.185$7,185GPU estimate | 1.57 |
| 52 | GLiDE 2B NVIDIA DGX Spark (GB10) · decision · late entry Open · 1.9BDetails | 67.461.0–74.5 | 46.7 | $0.058$58.31GPU estimate | 0.33 |
| 53 | KnowLine-0.8B-Gen1 NVIDIA DGX Spark (GB10) · decision · late entry Open · 0.8BDetails | 71.966.2–77.9 | 45.2 | $0.049$48.93GPU estimate | 0.11 |
| 54 | GLiDE 0.8B NVIDIA DGX Spark (GB10) · decision · late entry Open · 0.8BDetails | 80.471.8–89.3 | 41.7 | $0.051$51.47GPU estimate | 0.22 |
| 55 | OneJev1.6-0.8B NVIDIA DGX Spark (GB10) · decision · late entry Open · 0.9BDetails | 82.575.2–90.8 | 42.5 | $0.052$51.90GPU estimate | 0.10 |
| 56 | GLiDE 0.4B NVIDIA DGX Spark (GB10) · decision · late entry Open · 0.4BDetails | 113.2102.1–124.1 | 28.9 | $0.057$57.11GPU estimate | 0.13 |
| 57 | GLiClass v4 Edge NVIDIA DGX Spark (GB10) · decision · late entry Open · 0.4BDetails | 133.5118.5–148.8 | 21.5 | $0.174$174GPU estimate | 1.33 |
| GNUbg weak programDetails | 21.418.8–24.3 | 67.1 | – | 0.01 | |
| GNUbg weak programDetails | 27.024.1–29.8 | 62.3 | – | 0.01 | |
| GNUbg weak programDetails | 28.125.0–31.4 | 62.1 | – | 0.01 | |
| Safest programDetails | 51.647.4–56.2 | 50.0 | – | 0.00 | |
| Safest (computed) programDetails | – | 50.0 | – | Not measured | |
| Safest (computed) programDetails | – | 50.0 | – | Not measured | |
| Random programDetails | 121.1113.3–128.5 | 24.9 | – | 0.00 | |
| Random (computed) programDetails | – | 27.0 | – | Not measured | |
| Random (computed) programDetails | – | 27.6 | – | Not measured |
No model of this kind on the leaderboard.
One row per model at its highest reasoning setting, never its best score; late entries included. All setups: every setup of every model. How rows are chosen
Leagues played different positions; close scores across leagues need not mean a real difference. *
Rank counts 1, 2, 3 down the rows shown, by the measure shown (with a filter on, among those rows only); it has no tiers: a tier needs a paired test (McNemar, Holm) over positions every model answered, and each league played its own positions, so models in different leagues never answered the same ones. The tier in each row's details and Same positions (preview) come from 200 positions every model there answered. Rank comes from league play; tier comes from the same 200 positions for every model. Ranks show observed scores; small gaps need not be meaningful.
$ per 1,000 decisions: At each setup's price basis (a list price, or API-equivalent for a subscription); not a bill paid. Each cost's tag opens how it was counted; each row's details name its price basis.
Class: by the maker's total parameters, or by list price when the size is undisclosed *
Size by total parameters, as disclosed by the maker (for MoE models the label also shows active parameters): Tiny under 6B · Small 6B–15B · Medium over 15B up to 40B · Large over 40B. Models of undisclosed size, by standard list price per 1M input tokens: Efficient up to $0.50 · Workhorse up to $3 · Flagship over $3.
Cost per 1,000 decisions all leagues · lower is better
No model of this kind on the leaderboard.
- PelaAI
- Fastino
- OmniJev
- StartLux
- Inception
- Apertix AI
- Liquid AI
- Subquadratic
- Celeris
- TypeSafe
- Knowledgator
- Nace.AI
- Alibaba
- Turion.AI
- OpenAI
- Base Labs
- Sthānika AI
- REAX
- Z.ai
- Moonshot
- Cloudflare
- Perplexity
- Meta
- Zefan Cai
- EldanRing
- Blockbrain Labs
- Anthropic
- DeepSeek
- xAI
- program
| Counts 1, 2, 3 down the rows shown, by the measure chosen; no tiers. | The model and its setting. Tap or point at a name for its details. | Dollars per 1,000 decisions at each setup's price basis (a list price, or API-equivalent for a subscription); not a bill paid. Lower is better. | 100 = every call right, 50 = always safe; higher is better. | 500 × mean 2-ply equity loss per decision, the checker-play performance rating (PR) backgammon players use; lower is better. | Median request seconds per decision (waits between retries not included). Lower is better. |
|---|---|---|---|---|---|
| 1 | KnowLine-0.8B-Gen1 NVIDIA DGX Spark (GB10) · decision · late entry Open · 0.8BDetails | $0.049$48.93GPU estimate | 45.2 | 71.9 | 0.11 |
| 2 | KnowLine-2B-Gen1 NVIDIA DGX Spark (GB10) · decision · late entry Open · 2.0BDetails | $0.049$49.34GPU estimate | 51.1 | 54.5 | 0.15 |
| 3 | GLiDE 0.8B NVIDIA DGX Spark (GB10) · decision · late entry Open · 0.8BDetails | $0.051$51.47GPU estimate | 41.7 | 80.4 | 0.22 |
| 4 | OneJev1.6-0.8B NVIDIA DGX Spark (GB10) · decision · late entry Open · 0.9BDetails | $0.052$51.90GPU estimate | 42.5 | 82.5 | 0.10 |
| 5 | StartLux-Decision-v1.1-2B-Instant NVIDIA DGX Spark (GB10) · decision · late entry Open · 2.0BDetails | $0.052$52.30GPU estimate | 53.8 | 50.0 | 0.21 |
| 6 | StartLux-Decision-v1.1-0.8B-Instant NVIDIA DGX Spark (GB10) · decision · late entry Open · 0.8BDetails | $0.054$53.72GPU estimate | 44.6 | 64.7 | 0.13 |
| 7 | KnowLine 4B Gen5.5 NVIDIA DGX Spark (GB10) · decision · late entry Open · 4.0BDetails | $0.054$53.72GPU estimate | 49.7 | 53.6 | 0.28 |
| 8 | GLiDE 0.4B NVIDIA DGX Spark (GB10) · decision · late entry Open · 0.4BDetails | $0.057$57.11GPU estimate | 28.9 | 113.2 | 0.13 |
| 9 | GLiDE 2B NVIDIA DGX Spark (GB10) · decision · late entry Open · 1.9BDetails | $0.058$58.31GPU estimate | 46.7 | 67.4 | 0.33 |
| 10 | Mercury Decide decision Closed · EfficientDetails | $0.071$71.34List price | 53.4 | 47.9 | 0.48 |
| 11 | StartLux-Decision-v1.1-4B-Instant NVIDIA DGX Spark (GB10) · decision · late entry Open · 4.0BDetails | $0.072$71.58GPU estimate | 57.2 | 40.1 | 0.44 |
| 12 | Cerno 9B v1.2 NVIDIA DGX Spark (GB10) · decision · late entry Open · 9.0BDetails | $0.139$139GPU estimate | 56.1 | 48.5 | 1.96 |
| 13 | d1-ultra decision Closed · EfficientDetails | $0.145$145List price | 64.0 | 30.3 | 0.23 |
| 14 | SubQ Snap 1.1 decision · late entry Closed · EfficientDetails | $0.150$150Billed | 56.7 | 40.2 | 0.23 |
| 15 | celeris-1-decision decision Closed · EfficientDetails | $0.150$150List price | 57.8 | 35.6 | 0.17 |
| 16 | GLiDE API · decision Closed · EfficientDetails | $0.153$153List price | 60.4 | 33.2 | 0.48 |
| 17 | Jev 1.13 decision Closed · EfficientDetails | $0.166$166List price | 59.5 | 34.4 | 0.22 |
| 18 | Jev 1.14 decision Closed · EfficientDetails | $0.173$173List price | 59.3 | 31.7 | 0.19 |
| 19 | GLiClass v4 Edge NVIDIA DGX Spark (GB10) · decision · late entry Open · 0.4BDetails | $0.174$174GPU estimate | 21.5 | 133.5 | 1.33 |
| 20 | SubQ Snap Preview decision Closed · EfficientDetails | $0.193$193List price | 56.5 | 43.9 | 0.24 |
| 21 | Drex 2.0 API · decision · late entry Open · 35B MoE · 3.0B activeDetails | $0.258$258Billed | 58.1 | 38.4 | 0.42 |
| Drex 2.0 NVIDIA RTX PRO 6000 Blackwell · decision · late entry Open · 35B MoE · 3.0B activeDetails | $0.782$782GPU estimate | 53.0 | 42.9 | 0.40 | |
| 22 | Drex Max v1.1 decision · late entry Closed · Efficient (provisional)Details | $0.265$265List price | 59.1 | 30.9 | 0.44 |
| 23 | Qwen3.8 Flash off · chat Closed · EfficientDetails | $0.284$284List price | 59.5 | 33.6 | 1.70 |
| 24 | Turion Jev 31B NVIDIA DGX Spark (GB10) · decision · late entry Open · 31BDetails | $0.293$293GPU estimate | 59.6 | 29.7 | 3.95 |
| 25 | GPT-6 Luna Decisions API · decision Closed · EfficientDetails | $0.335$335List price | 55.7 | 43.3 | 0.23 |
| 26 | Gemini Decision 1 20261111 · decision · late entry Closed · EfficientDetails | $0.382$382Billed | 64.7 | 28.0 | 0.24 |
| 27 | d1-2B NVIDIA RTX PRO 6000 Blackwell · decision · late entry Open · 1.9BDetails | $0.467$467GPU estimate | 55.2 | 47.1 | 0.06 |
| 28 | d1-Omni-2B NVIDIA RTX PRO 6000 Blackwell · decision · late entry Open · 2.2BDetails | $0.657$657GPU estimate | 53.2 | 49.8 | 0.06 |
| 29 | Elephant-1 NVIDIA RTX PRO 6000 Blackwell · decision · late entry Open · 9.0BDetails | $0.685$685GPU estimate | 57.7 | 44.6 | 0.26 |
| 30 | Sieve 31B v3 NVIDIA DGX Spark (GB10) · decision · late entry Open · 31BDetails | $0.794$794GPU estimate | 62.7 | 27.5 | 11.1 |
| 31 | Mammoth-1 NVIDIA RTX PRO 6000 Blackwell · decision · late entry Open · 27BDetails | $0.999$999GPU estimate | 63.2 | 28.5 | 0.72 |
| 32 | Drex Max NVIDIA RTX PRO 6000 Blackwell · decision · late entry Open · 27BDetails | $1.285$1,285GPU estimate | 62.9 | 30.4 | 0.68 |
| 33 | REAX 1.3 NVIDIA RTX PRO 6000 Blackwell · decision · late entry Open · 57BDetails | $1.545$1,545GPU estimate | 60.5 | 27.8 | 1.74 |
| 34 | GLM-5.3 low · chat Open · 753B MoEDetails | $2.917$2,917List price | 61.7 | 30.9 | 1.75 |
| 35 | Kimi K3.1 Pro off · chat Open · 2.8T MoE · 104B activeDetails | $3.982$3,982List price | 65.9 | 28.0 | 2.11 |
| 36 | Clef NVIDIA RTX PRO 6000 Blackwell + NVIDIA DGX Spark · decision Open · 27BDetails | $5.736$5,736GPU estimate | 57.5 | 36.5 | 1.13 |
| 37 | Perplexity Decider 27B v1.1 NVIDIA RTX PRO 6000 Blackwell + NVIDIA DGX Spark · decision Open · 27BDetails | $6.593$6,593GPU estimate | 56.9 | 38.8 | 1.97 |
| 38 | Muse Ember max · chat · late entry Closed · EfficientDetails | $6.863$6,863Billed | 66.0 | 20.1 | 15.3 |
| 39 | Open-Jev-27B-v1.1 NVIDIA RTX PRO 6000 Blackwell · decision Open · 27BDetails | $7.185$7,185GPU estimate | 48.5 | 65.6 | 1.57 |
| 40 | Winnow-12B NVIDIA RTX PRO 6000 Blackwell · decision Open · 12BDetails | $9.615$9,615GPU estimate | 55.2 | 49.7 | 2.46 |
| 41 | GLiDE v1.2 · NVIDIA RTX PRO 6000 Blackwell · decision Open · 27BDetails | $10.301$10,301GPU estimate | 58.8 | 35.0 | 1.41 |
| 42 | Cygnet NVIDIA RTX PRO 6000 Blackwell + NVIDIA DGX Spark · decision Open · 12BDetails | $11.168$11,168GPU estimate | 57.1 | 38.6 | 0.37 |
| 43 | Perplexity Decider 27B v1.2 NVIDIA RTX PRO 6000 Blackwell · decision Open · 27BDetails | $12.227$12,227GPU estimate | 57.9 | 36.9 | 0.94 |
| 44 | Perplexity Decider Flash v1.2 NVIDIA RTX PRO 6000 Blackwell · decision Open · 4.0BDetails | $12.267$12,267GPU estimate | 49.1 | 59.6 | 0.56 |
| 45 | GPT-6.1 Sol high · chat Closed · WorkhorseDetails | $15.573$15,573List price | 72.2 | 9.9 | 13.1 |
| GPT-6.1 Sol low · chat Closed · WorkhorseDetails | $10.228$10,228List price | 72.7 | 12.1 | 4.33 | |
| 46 | Claude Sonnet 5.5 high · chat Closed · WorkhorseDetails | $19.847$19,847List price | 68.2 | 16.7 | 6.63 |
| Claude Sonnet 5.5 low · chat Closed · WorkhorseDetails | $13.541$13,541List price | 63.5 | 20.1 | 1.51 | |
| 47 | Gemini 3.8 Flash high · chat Closed · WorkhorseDetails | $22.352$22,352List price | 66.9 | 14.9 | 9.59 |
| Gemini 3.8 Flash low · chat Closed · WorkhorseDetails | $4.123$4,123List price | 65.1 | 16.3 | 2.16 | |
| 48 | Gemma 4 31B on · NVIDIA RTX PRO 6000 Blackwell + NVIDIA DGX Spark · chat Open · 31BDetails | $34.943$34,943GPU estimate | 64.5 | 19.6 | 120.6 |
| Gemma 4 31B off · NVIDIA RTX PRO 6000 Blackwell + NVIDIA DGX Spark · chat Open · 31BDetails | $8.215$8,215GPU estimate | 62.6 | 22.5 | 0.31 | |
| 49 | Claude Opus 5.5 high · chat Closed · FlagshipDetails | $36.400$36,400List price | 70.0 | 14.4 | 6.35 |
| Claude Opus 5.5 low · chat Closed · FlagshipDetails | $29.062$29,062List price | 66.9 | 15.4 | 3.92 | |
| 50 | LFM2.5-24B-A2B on · NVIDIA RTX PRO 6000 Blackwell + NVIDIA DGX Spark · chat Open · 24B MoE · 2.5B activeDetails | $38.716$38,716GPU estimate | 52.4 | 47.7 | 324.8 |
| LFM2.5-24B-A2B off · NVIDIA RTX PRO 6000 Blackwell · chat Open · 24B MoE · 2.5B activeDetails | $9.132$9,132GPU estimate | 45.7 | 61.5 | 0.14 | |
| 51 | Qwen3.8-27B low · NVIDIA RTX PRO 6000 Blackwell + NVIDIA DGX Spark · chat Open · 27BDetails | $39.023$39,023GPU estimate | 62.0 | 29.0 | 171.1 |
| Qwen3.8-27B off · NVIDIA RTX PRO 6000 Blackwell + NVIDIA DGX Spark · chat Open · 27BDetails | $4.551$4,551GPU estimate | 57.6 | 45.0 | 1.48 | |
| 52 | DeepSeek-V4.1-Flash low · API + NVIDIA RTX PRO 6000 Blackwell · first release · chat Open · 552B MoE · 16B activeDetails | $47.092$47,092GPU estimate | 69.0 | 19.0 | 43.8 |
| DeepSeek-V4.1-Flash off · API · 1017 · chat Open · 552B MoE · 16B activeDetails | $0.244$244List price | 58.5 | 35.2 | 0.84 | |
| DeepSeek-V4.1-Flash off · API + NVIDIA RTX PRO 6000 Blackwell · first release · chat Open · 552B MoE · 16B activeDetails | $0.728$728GPU estimate | 59.3 | 35.6 | 0.48 | |
| DeepSeek-V4.1-Flash low · API · 1017 · chat Open · 552B MoE · 16B activeDetails | $4.869$4,869List price | 68.5 | 17.1 | 22.3 | |
| 53 | GPT-6 Astra high · chat · late entry Closed · FlagshipDetails | $59.356$59,356List price | 74.4 | 8.8 | 9.83 |
| GPT-6 Astra low · chat Closed · FlagshipDetails | $49.737$49,737List price | 75.8 | 11.8 | 3.94 | |
| GPT-6 Astra medium · chat Closed · FlagshipDetails | $50.268$50,268List price | 74.7 | 11.1 | 4.40 | |
| 54 | Gemini 4 Argon high · chat Closed · FlagshipDetails | $64.401$64,401List price | 74.1 | 12.6 | 27.5 |
| Gemini 4 Argon low · chat Closed · FlagshipDetails | $10.204$10,204List price | 69.2 | 16.5 | 3.82 | |
| 55 | Grok 4.7 high · chat Closed · WorkhorseDetails | $117.379$117,379List price | 68.5 | 18.8 | 122.3 |
| Grok 4.7 low · chat Closed · WorkhorseDetails | $32.813$32,813List price | 67.7 | 19.1 | 24.3 | |
| 56 | Claude Fable 5.1 high · chat Closed · FlagshipDetails | $136.268$136,268List price | 72.3 | 14.0 | 12.7 |
| Claude Fable 5.1 low · chat Closed · FlagshipDetails | $62.613$62,613List price | 67.8 | 17.9 | 1.54 | |
| – | KnowLine-31B-Gen1.5 NVIDIA DGX Spark (GB10) · decision · late entry Open · 31BDetails | – | 61.6 | 26.2 | 3.45 |
| GNUbg weak programDetails | – | 67.1 | 21.4 | 0.01 | |
| GNUbg weak programDetails | – | 62.3 | 27.0 | 0.01 | |
| GNUbg weak programDetails | – | 62.1 | 28.1 | 0.01 | |
| Safest programDetails | – | 50.0 | 51.6 | 0.00 | |
| Safest (computed) programDetails | – | 50.0 | – | Not measured | |
| Safest (computed) programDetails | – | 50.0 | – | Not measured | |
| Random programDetails | – | 24.9 | 121.1 | 0.00 | |
| Random (computed) programDetails | – | 27.0 | – | Not measured | |
| Random (computed) programDetails | – | 27.6 | – | Not measured |
No model of this kind on the leaderboard.
One row per model at its highest reasoning setting, never its best score; late entries included. All setups: every setup of every model. How rows are chosen
Leagues played different positions; close scores across leagues need not mean a real difference. *
Rank counts 1, 2, 3 down the rows shown, by the measure shown (with a filter on, among those rows only); it has no tiers: a tier needs a paired test (McNemar, Holm) over positions every model answered, and each league played its own positions, so models in different leagues never answered the same ones. The tier in each row's details and Same positions (preview) come from 200 positions every model there answered. Rank comes from league play; tier comes from the same 200 positions for every model. Ranks show observed scores; small gaps need not be meaningful.
$ per 1,000 decisions: At each setup's price basis (a list price, or API-equivalent for a subscription); not a bill paid. Each cost's tag opens how it was counted; each row's details name its price basis.
Class: by the maker's total parameters, or by list price when the size is undisclosed *
Size by total parameters, as disclosed by the maker (for MoE models the label also shows active parameters): Tiny under 6B · Small 6B–15B · Medium over 15B up to 40B · Large over 40B. Models of undisclosed size, by standard list price per 1M input tokens: Efficient up to $0.50 · Workhorse up to $3 · Flagship over $3.
Details of each setup
GPT-6 Astra · OpenAI · chat model · high
Risk judgement 74.4 (95%: 71.8–77.0)
Risks found 53.3% · safe right 95.5%
Took 248 of 465 risks that paid · played safe in 614 of 643 positions where safe paid
Error rate 8.8 (95%: 7.4–10.3) · record 10–1–1 · late entry
Played the original League 3 field after the league finished (late entry)
$59.356 per 1,000 decisions$59.356 per 1M decisions (API-equivalent (subscription)) · 1,489 decisions
Parameters: not disclosed by maker
Closed · Flagship ($10 per 1M input tokens, standard list price).
Tier (same positions) not run yet
Released Sep 2026
Did they improve? pending
GPT-6 Astra · OpenAI · chat model · low
Risk judgement 75.8 (95%: 73.1–78.5)
Risks found 57.2% · safe right 94.4%
Took 226 of 395 risks that paid · played safe in 486 of 515 positions where safe paid
Error rate 11.8 (95%: 9.5–14.2) · record 4–1–6
League 3
$49.737 per 1,000 decisions$49.737 per 1M decisions (API-equivalent (subscription)) · 1,251 decisions
Parameters: not disclosed by maker
Closed · Flagship ($10 per 1M input tokens, standard list price).
Tier (same positions) not run yet
Released Sep 2026
Did they improve? not in the learning plan
GPT-6 Astra · OpenAI · chat model · medium
Risk judgement 74.7 (95%: 71.9–77.3)
Risks found 54.9% · safe right 94.4%
Took 245 of 446 risks that paid · played safe in 542 of 574 positions where safe paid
Error rate 11.1 (95%: 9.5–12.9) · record 8–0–3
League 3
$50.268 per 1,000 decisions$50.268 per 1M decisions (API-equivalent (subscription)) · 1,362 decisions
Parameters: not disclosed by maker
Closed · Flagship ($10 per 1M input tokens, standard list price).
Tier (same positions) not run yet
Released Sep 2026
Did they improve? not in the learning plan
Gemini 4 Argon · Google · chat model · high
Risk judgement 74.1 (95%: 72.0–76.1)
Risks found 50.8% · safe right 97.4%
Took 224 of 441 risks that paid · played safe in 484 of 497 positions where safe paid
Error rate 12.6 (95%: 10.5–14.8) · record 4–1–6
League 3
$64.401 per 1,000 decisions$64.401 per 1M decisions (API-equivalent (subscription)) · 1,368 decisions
Parameters: not disclosed by maker
Closed · Flagship ($4 per 1M input tokens, standard list price).
Tier (same positions) 1
Released Oct 2026
Did they improve? Yes · +8.5 pp · threshold 5.0 pp
Gemini 4 Argon · Google · chat model · low
Risk judgement 69.2 (95%: 66.2–72.3)
Risks found 47.8% · safe right 90.7%
Took 209 of 437 risks that paid · played safe in 543 of 599 positions where safe paid
Error rate 16.5 (95%: 13.7–19.5) · record 3–1–7
League 3
$10.204 per 1,000 decisions$10.204 per 1M decisions (API-equivalent (subscription)) · 1,484 decisions
Parameters: not disclosed by maker
Closed · Flagship ($4 per 1M input tokens, standard list price).
Tier (same positions) not run yet
Released Oct 2026
Did they improve? not in the learning plan
Claude Fable 5.1 · Anthropic · chat model · high
Risk judgement 72.3 (95%: 69.8–74.7)
Risks found 50.7% · safe right 94.0%
Took 215 of 424 risks that paid · played safe in 529 of 563 positions where safe paid
Error rate 14.0 (95%: 11.5–16.3) · record 6–0–5
League 3
$136.268 per 1,000 decisions$136.268 per 1M decisions (API-equivalent (subscription)) · 1,286 decisions
Parameters: not disclosed by maker
Closed · Flagship ($10 per 1M input tokens, standard list price).
Tier (same positions) 1
Released Sep 2026
Did they improve? Yes · +9.4 pp · threshold 5.0 pp
Claude Fable 5.1 · Anthropic · chat model · low
Risk judgement 67.8 (95%: 65.6–69.9)
Risks found 41.0% · safe right 94.6%
Took 270 of 658 risks that paid · played safe in 781 of 826 positions where safe paid
Error rate 17.9 (95%: 15.9–20.1) · record 10–0–8
League 2
$62.613 per 1,000 decisions$62.613 per 1M decisions (API-equivalent (subscription)) · 2,008 decisions
Parameters: not disclosed by maker
Closed · Flagship ($10 per 1M input tokens, standard list price).
Tier (same positions) not run yet
Released Sep 2026
Did they improve? not in the learning plan
GPT-6.1 Sol · OpenAI · chat model · high
Risk judgement 72.2 (95%: 69.5–74.9)
Risks found 50.6% · safe right 93.7%
Took 212 of 419 risks that paid · played safe in 568 of 606 positions where safe paid
Error rate 9.9 (95%: 8.6–11.3) · record 7–0–4
League 3
$15.573 per 1,000 decisions$15.573 per 1M decisions (API-equivalent (subscription)) · 1,389 decisions
Parameters: not disclosed by maker
Closed · Workhorse ($2 per 1M input tokens, standard list price).
Tier (same positions) not run yet
Released Sep 2026
Did they improve? pending
GPT-6.1 Sol · OpenAI · chat model · low
Risk judgement 72.7 (95%: 69.9–75.5)
Risks found 51.7% · safe right 93.8%
Took 198 of 383 risks that paid · played safe in 602 of 642 positions where safe paid
Error rate 12.1 (95%: 10.5–13.7) · record 9–0–2
League 3
$10.228 per 1,000 decisions$10.228 per 1M decisions (API-equivalent (subscription)) · 1,344 decisions
Parameters: not disclosed by maker
Closed · Workhorse ($2 per 1M input tokens, standard list price).
Tier (same positions) not run yet
Released Sep 2026
Did they improve? not in the learning plan
Claude Opus 5.5 · Anthropic · chat model · high
Risk judgement 70.0 (95%: 67.3–72.6)
Risks found 43.4% · safe right 96.6%
Took 199 of 459 risks that paid · played safe in 590 of 611 positions where safe paid
Error rate 14.4 (95%: 12.1–17.0) · record 6–0–5
League 3
$36.400 per 1,000 decisions$36.400 per 1M decisions (API-equivalent (subscription)) · 1,477 decisions
Parameters: not disclosed by maker
Closed · Flagship ($4 per 1M input tokens, standard list price).
Tier (same positions) 1
Released Sep 2026
Did they improve? Yes · +6.7 pp · threshold 5.0 pp
Claude Opus 5.5 · Anthropic · chat model · low
Risk judgement 66.9 (95%: 64.7–69.2)
Risks found 40.1% · safe right 93.8%
Took 187 of 466 risks that paid · played safe in 541 of 577 positions where safe paid
Error rate 15.4 (95%: 13.1–18.0) · record 4–0–7
League 3
$29.062 per 1,000 decisions$29.062 per 1M decisions (API-equivalent (subscription)) · 1,411 decisions
Parameters: not disclosed by maker
Closed · Flagship ($4 per 1M input tokens, standard list price).
Tier (same positions) not run yet
Released Sep 2026
Did they improve? not in the learning plan
DeepSeek-V4.1-Flash · DeepSeek · chat model · low · API + NVIDIA RTX PRO 6000 Blackwell · first release
Risk judgement 69.0 (95%: 67.3–70.9)
Risks found 45.0% · safe right 93.0%
Took 338 of 751 risks that paid · played safe in 891 of 958 positions where safe paid
Error rate 19.0 (95%: 16.6–21.3) · record 12–0–6
League 2
$47.092 per 1,000 decisions$47.092 per 1M decisions (estimate · RTX PRO 6000 Blackwell + API) · 2,226 decisions
Cost: Estimate: $47.092 per 1,000 decisions (GPU time, at most). Counted as the wall clock from the first to the last answer, pauses over 10 min left out, × the hourly rate ÷ decisions. 8.2 h on 4 × NVIDIA RTX PRO 6000 Blackwell (96 GB) × $2.49/h × 4 = $81.21; plus 1,556 answers from the hosted API at their recorded cost, $23.62; total $104.83 ÷ 2,226 decisions; left out: 38 gaps over 10 min between consecutive answers, 33.3 h in all (each one listed in the data file). NVIDIA RTX PRO 6000 Blackwell (96 GB): $2.49/h per GPU. Other setups' servers may have run on the same machine at the same time; each setup is charged the whole device, so this is an upper bound.
Parameters: 552B backbone + 196B conditional memory; active 8B (prefill) / 16B (decode) · MoE
Mixture of experts: 552B total, about 16B active per step, 8B per token in prefill and 16B in decode (the maker's figures).
Tier (same positions) 1
Released Sep 2026
With its dated checkpoint DeepSeek-V4.1-Flash1017 (its own rows under All setups)
Did they improve? Yes · +8.2 pp · threshold 5.0 pp
DeepSeek-V4.1-Flash · DeepSeek · chat model · low · API · 1017
Risk judgement 68.5 (95%: 66.4–70.6)
Risks found 42.5% · safe right 94.5%
Took 321 of 755 risks that paid · played safe in 872 of 923 positions where safe paid
Error rate 17.1 (95%: 15.1–19.2) · record 12–1–5
League 2
$4.869 per 1,000 decisions$4.869 per 1M decisions (API price) · 2,234 decisions
Parameters: not disclosed by maker
Mixture of experts: 552B total, about 16B active per step, 8B per token in prefill and 16B in decode (the maker's figures).
Tier (same positions) not run yet
Released Sep 2026
Did they improve? not in the learning plan
DeepSeek-V4.1-Flash · DeepSeek · chat model · off · API + NVIDIA RTX PRO 6000 Blackwell · first release
Risk judgement 59.3 (95%: 57.1–61.5)
Risks found 29.1% · safe right 89.5%
Took 192 of 659 risks that paid · played safe in 603 of 674 positions where safe paid
Error rate 35.6 (95%: 31.7–39.7) · record 12–0–6
League 1
$0.728 per 1,000 decisions$0.728 per 1M decisions (estimate · RTX PRO 6000 Blackwell + API) · 1,736 decisions
Cost: Estimate: $0.728 per 1,000 decisions (GPU time, at most). Counted as the wall clock from the first to the last answer, pauses over 10 min left out, × the hourly rate ÷ decisions. 0.07 h on 4 × NVIDIA RTX PRO 6000 Blackwell (96 GB) × $2.49/h × 4 = $0.65; plus 1,641 answers from the hosted API at their recorded cost, $0.61; total $1.26 ÷ 1,736 decisions; left out: 7 gaps over 10 min between consecutive answers, 30.8 h in all (each one listed in the data file). NVIDIA RTX PRO 6000 Blackwell (96 GB): $2.49/h per GPU. Other setups' servers may have run on the same machine at the same time; each setup is charged the whole device, so this is an upper bound.
Parameters: 552B backbone + 196B conditional memory; active 8B (prefill) / 16B (decode) · MoE
Mixture of experts: 552B total, about 16B active per step, 8B per token in prefill and 16B in decode (the maker's figures).
Tier (same positions) not run yet
Released Sep 2026
Did they improve? not in the learning plan
DeepSeek-V4.1-Flash · DeepSeek · chat model · off · API · 1017
Risk judgement 58.5 (95%: 56.6–60.5)
Risks found 25.4% · safe right 91.7%
Took 181 of 713 risks that paid · played safe in 683 of 745 positions where safe paid
Error rate 35.2 (95%: 31.8–38.8) · record 5–1–12
League 2
$0.244 per 1,000 decisions$0.244 per 1M decisions (API price) · 2,034 decisions
Parameters: not disclosed by maker
Mixture of experts: 552B total, about 16B active per step, 8B per token in prefill and 16B in decode (the maker's figures).
Tier (same positions) not run yet
Released Sep 2026
Did they improve? not in the learning plan
Grok 4.7 · xAI · chat model · high
Risk judgement 68.5 (95%: 66.1–71.1)
Risks found 44.0% · safe right 93.0%
Took 190 of 432 risks that paid · played safe in 454 of 488 positions where safe paid
Error rate 18.8 (95%: 15.9–21.8) · record 6–1–4
League 3
$117.379 per 1,000 decisions$117.379 per 1M decisions (API-equivalent (subscription)) · 1,337 decisions
Parameters: not disclosed by maker
Closed · Workhorse ($2 per 1M input tokens, standard list price).
Tier (same positions) 1
Released Sep 2026
Did they improve? pending
Grok 4.7 · xAI · chat model · low
Risk judgement 67.7 (95%: 66.0–69.5)
Risks found 42.3% · safe right 93.0%
Took 295 of 697 risks that paid · played safe in 852 of 916 positions where safe paid
Error rate 19.1 (95%: 16.9–21.4) · record 11–0–7
League 2
$32.813 per 1,000 decisions$32.813 per 1M decisions (API-equivalent (subscription)) · 2,152 decisions
Parameters: not disclosed by maker
Closed · Workhorse ($2 per 1M input tokens, standard list price).
Tier (same positions) not run yet
Released Sep 2026
Did they improve? not in the learning plan
Claude Sonnet 5.5 · Anthropic · chat model · high
Risk judgement 68.2 (95%: 66.3–70.0)
Risks found 41.8% · safe right 94.6%
Took 308 of 737 risks that paid · played safe in 841 of 889 positions where safe paid
Error rate 16.7 (95%: 14.9–18.7) · record 12–0–6
League 2
$19.847 per 1,000 decisions$19.847 per 1M decisions (API-equivalent (subscription)) · 2,164 decisions
Parameters: not disclosed by maker
Closed · Workhorse ($2 per 1M input tokens, standard list price).
Tier (same positions) 1
Released Sep 2026
Did they improve? Yes · +7.0 pp · threshold 5.0 pp
Claude Sonnet 5.5 · Anthropic · chat model · low
Risk judgement 63.5 (95%: 61.6–65.4)
Risks found 30.9% · safe right 96.2%
Took 204 of 661 risks that paid · played safe in 883 of 918 positions where safe paid
Error rate 20.1 (95%: 17.8–22.4) · record 13–1–4
League 2
$13.541 per 1,000 decisions$13.541 per 1M decisions (API-equivalent (subscription)) · 2,150 decisions
Parameters: not disclosed by maker
Closed · Workhorse ($2 per 1M input tokens, standard list price).
Tier (same positions) not run yet
Released Sep 2026
Did they improve? not in the learning plan
Gemini 3.8 Flash · Google · chat model · high
Risk judgement 66.9 (95%: 65.2–68.5)
Risks found 36.1% · safe right 97.6%
Took 264 of 731 risks that paid · played safe in 858 of 879 positions where safe paid
Error rate 14.9 (95%: 12.9–17.0) · record 12–0–6
League 2
$22.352 per 1,000 decisions$22.352 per 1M decisions (API-equivalent (subscription)) · 2,168 decisions
Parameters: not disclosed by maker
Closed · Workhorse ($0.75 per 1M input tokens, standard list price).
Tier (same positions) 1
Released Sep 2026
Did they improve? Yes · +8.2 pp · threshold 5.0 pp
Gemini 3.8 Flash · Google · chat model · low
Risk judgement 65.1 (95%: 63.5–66.8)
Risks found 33.8% · safe right 96.5%
Took 214 of 633 risks that paid · played safe in 877 of 909 positions where safe paid
Error rate 16.3 (95%: 14.5–18.2) · record 14–2–2
League 2
$4.123 per 1,000 decisions$4.123 per 1M decisions (API-equivalent (subscription)) · 2,053 decisions
Parameters: not disclosed by maker
Closed · Workhorse ($0.75 per 1M input tokens, standard list price).
Tier (same positions) not run yet
Released Sep 2026
Did they improve? not in the learning plan
Muse Ember · Meta · chat model · max
Risk judgement 66.0 (95%: 63.9–68.2)
Risks found 37.6% · safe right 94.4%
Took 224 of 596 risks that paid · played safe in 671 of 711 positions where safe paid
Error rate 20.1 (95%: 17.6–22.7) · record 13–0–4 · late entry
Played the original League 1 field after the league finished (late entry)
17 of 19 matches · GPT-6 LunaDecisions API: outside the requested scope (Ümit, 12 Nov); not played (opponent's API out of credit) · Mercury Decide: outside the requested scope (Ümit, 12 Nov); not played (opponent no longer served on OpenRouter)
$6.863 per 1,000 decisions$6.863 per 1M decisions (API price (billed)) · 1,713 decisions
Parameters: not disclosed by maker
Closed · Efficient ($0.1 per 1M input tokens, standard list price).
Tier (same positions) 1
Did they improve? not in the learning plan
Kimi K3.1 Pro · Moonshot · chat model · off
Risk judgement 65.9 (95%: 63.2–68.9)
Risks found 42.4% · safe right 89.5%
Took 153 of 361 risks that paid · played safe in 416 of 465 positions where safe paid
Error rate 28.0 (95%: 24.5–31.8) · record 4–0–7
League 3
$3.982 per 1,000 decisions$3.982 per 1M decisions (API price) · 1,167 decisions
Parameters: 2.8T MoE · 104B active
Mixture of experts: 2.8T total, about 104B active per step (the maker's figures).
Tier (same positions) 1
Released Oct 2026
Did they improve? No · +4.8 pp · threshold 5.0 pp
Gemini Decision 1 · Google · decision model · 20261111
Risk judgement 64.7 (95%: 62.2–67.2)
Risks found 40.9% · safe right 88.5%
Took 219 of 535 risks that paid · played safe in 648 of 732 positions where safe paid
Error rate 28.0 (95%: 25.0–31.1) · record 13–0–4 · late entry
Played the original League 1 field after the league finished (late entry)
17 of 19 matches · GPT-6 LunaDecisions API: outside the requested scope (Ümit, 12 Nov); not played (opponent's API out of credit) · Mercury Decide: outside the requested scope (Ümit, 12 Nov); not played (opponent no longer served on OpenRouter)
$0.382 per 1,000 decisions$0.382 per 1M decisions (API price (billed)) · 1,704 decisions
Parameters: not disclosed by maker
Closed · Efficient ($0.1 per 1M input tokens, standard list price).
Tier (same positions) not run yet
Did they improve? not in the learning plan
Gemma 4 31B · Google · chat model · on · NVIDIA RTX PRO 6000 Blackwell + NVIDIA DGX Spark
Risk judgement 64.5 (95%: 62.9–66.2)
Risks found 31.9% · safe right 97.1%
Took 223 of 700 risks that paid · played safe in 878 of 904 positions where safe paid
Error rate 19.6 (95%: 17.5–21.7) · record 13–0–5
League 2
$34.943 per 1,000 decisions$34.943 per 1M decisions (estimate · RTX PRO 6000 Blackwell) · 2,122 decisions
Cost: Estimate: $34.943 per 1,000 decisions (GPU time, at most). Counted as the wall clock from the first to the last answer, pauses over 10 min left out, × the hourly rate ÷ decisions. 1.3 h on NVIDIA DGX Spark (GB10) × $0.213/h = $0.27 + 22.1 h on NVIDIA RTX PRO 6000 Blackwell (96 GB) × $2.49/h = $55.13 + 3.8 h on 2 × NVIDIA RTX PRO 6000 Blackwell (96 GB) × $2.49/h × 2 = $18.75; total $74.15 ÷ 2,122 decisions; left out: 62 gaps over 10 min between consecutive answers, 134.0 h in all (each one listed in the data file). NVIDIA RTX PRO 6000 Blackwell (96 GB): $2.49/h per GPU. NVIDIA DGX Spark (GB10): CHF 4,000 ÷ (3 years × 8,760 h) = CHF 0.152/h purchase + CHF 0.2838/kWh (ewz.natur high rate) × 0.0791 kW (the chip's measured draw, not the whole box) = CHF 0.022/h electricity; CHF 0.175/h ≈ $0.213/h (CHF 1 = $1.2185, ECB 2026-11-10). Other setups' servers may have run on the same machine at the same time; each setup is charged the whole device, so this is an upper bound.
Parameters: 31.27B incl. its vision encoder · dense
Size class by the maker's figure, 30.7B; our checkpoint count 31.27B.
Tier (same positions) 1
Released Apr 2026
Did they improve? Yes · +8.5 pp · threshold 5.0 pp
Gemma 4 31B · Google · chat model · off · NVIDIA RTX PRO 6000 Blackwell + NVIDIA DGX Spark
Risk judgement 62.6 (95%: 60.4–65.0)
Risks found 33.2% · safe right 92.1%
Took 194 of 584 risks that paid · played safe in 732 of 795 positions where safe paid
Error rate 22.5 (95%: 19.9–25.3) · record 10–0–8
League 2
$8.215 per 1,000 decisions$8.215 per 1M decisions (estimate · RTX PRO 6000 Blackwell) · 1,847 decisions
Cost: Estimate: $8.215 per 1,000 decisions (GPU time, at most). Counted as the wall clock from the first to the last answer, pauses over 10 min left out, × the hourly rate ÷ decisions. 1.6 h on NVIDIA DGX Spark (GB10) × $0.213/h = $0.34 + 6.0 h on NVIDIA RTX PRO 6000 Blackwell (96 GB) × $2.49/h = $14.83; total $15.17 ÷ 1,847 decisions; left out: 10 gaps over 10 min between consecutive answers, 151.2 h in all (each one listed in the data file). NVIDIA RTX PRO 6000 Blackwell (96 GB): $2.49/h per GPU. NVIDIA DGX Spark (GB10): CHF 4,000 ÷ (3 years × 8,760 h) = CHF 0.152/h purchase + CHF 0.2838/kWh (ewz.natur high rate) × 0.0791 kW (the chip's measured draw, not the whole box) = CHF 0.022/h electricity; CHF 0.175/h ≈ $0.213/h (CHF 1 = $1.2185, ECB 2026-11-10). Other setups' servers may have run on the same machine at the same time; each setup is charged the whole device, so this is an upper bound.
Parameters: 31.27B incl. its vision encoder · dense
Size class by the maker's figure, 30.7B; our checkpoint count 31.27B.
Tier (same positions) not run yet
Released Apr 2026
Did they improve? not in the learning plan
d1-ultra · Liquid AI · decision model
Risk judgement 64.0 (95%: 61.7–66.3)
Risks found 42.0% · safe right 86.0%
Took 289 of 688 risks that paid · played safe in 702 of 816 positions where safe paid
Error rate 30.3 (95%: 27.3–33.4) · record 6–1–11
League 2
$0.145 per 1,000 decisions$0.145 per 1M decisions (API price) · 2,071 decisions
Parameters: not disclosed by maker
Closed · Efficient ($0.042 per 1M input tokens, standard list price).
Tier (same positions) not run yet
Released Oct 2026
Did they improve? (decision models, two arms) not tested (conservative context guard)
Mammoth-1 · Base Labs · decision model · NVIDIA RTX PRO 6000 Blackwell
Risk judgement 63.2 (95%: 61.2–65.2)
Risks found 40.0% · safe right 86.4%
Took 288 of 720 risks that paid · played safe in 760 of 880 positions where safe paid
Error rate 28.5 (95%: 26.2–31.1) · record 16–1–2 · late entry
Played the original League 1 field after the league finished (late entry)
$0.999 per 1,000 decisions$0.999 per 1M decisions (estimate · RTX PRO 6000 Blackwell) · 2,021 decisions
Cost: Estimate: $0.999 per 1,000 decisions (GPU time, at most). Counted as the wall clock from the first to the last answer, pauses over 10 min left out, × the hourly rate ÷ decisions. 0.8 h on NVIDIA RTX PRO 6000 Blackwell (96 GB) × $2.49/h = $2.02; total $2.02 ÷ 2,021 decisions; left out: 1 gaps over 10 min between consecutive answers, 0.7 h in all (each one listed in the data file). NVIDIA RTX PRO 6000 Blackwell (96 GB): $2.49/h per GPU. Other setups' servers may have run on the same machine at the same time; each setup is charged the whole device, so this is an upper bound.
Parameters: 27.36B incl. its vision encoder; card: 27B · dense
Size class by the maker's figure, 27B; our checkpoint count 27.36B.
Tier (same positions) not run yet
Did they improve? (decision models, two arms) waiting (Ümit's D5 decision)
Drex Max · Nace.AI · decision model · NVIDIA RTX PRO 6000 Blackwell
Risk judgement 62.9 (95%: 61.1–64.7)
Risks found 39.3% · safe right 86.5%
Took 299 of 761 risks that paid · played safe in 775 of 896 positions where safe paid
Error rate 30.4 (95%: 27.4–33.4) · record 11–0–7 · late entry
Played the original League 1 field after the league finished (late entry)
18 of 19 matches · GPT-6 LunaDecisions API: outside the requested scope (Ümit, 12 Nov); not played (opponent's API out of credit)
$1.285 per 1,000 decisions$1.285 per 1M decisions (estimate · RTX PRO 6000 Blackwell) · 2,148 decisions
Cost: Estimate: $1.285 per 1,000 decisions (GPU time, at most). Counted as the wall clock from the first to the last answer, pauses over 10 min left out, × the hourly rate ÷ decisions. 1.1 h on NVIDIA RTX PRO 6000 Blackwell (96 GB) × $2.49/h = $2.76; total $2.76 ÷ 2,148 decisions; left out: 1 gaps over 10 min between consecutive answers, 5.3 h in all (each one listed in the data file). NVIDIA RTX PRO 6000 Blackwell (96 GB): $2.49/h per GPU. Other setups' servers may have run on the same machine at the same time; each setup is charged the whole device, so this is an upper bound.
Parameters: backbone 26.09B incl. its vision encoder + decision head 1.3M; card: 27B · dense
Size class by the maker's figure, 27B; our checkpoint count 26.09B.
Tier (same positions) not run yet
Did they improve? not in the learning plan
Sieve 31B v3 · Sthānika AI · decision model · NVIDIA DGX Spark (GB10)
Risk judgement 62.7 (95%: 60.6–64.9)
Risks found 35.2% · safe right 90.2%
Took 200 of 568 risks that paid · played safe in 696 of 772 positions where safe paid
Error rate 27.5 (95%: 24.1–31.6) · record 15–0–2 · late entry
Played the original League 1 field after the league finished (late entry)
17 of 19 matches · GPT-6 LunaDecisions API: outside the requested scope (Ümit, 12 Nov); not played (opponent's API out of credit) · Mercury Decide: outside the requested scope (Ümit, 12 Nov); not played (opponent no longer served on OpenRouter)
$0.794 per 1,000 decisions$0.794 per 1M decisions (estimate · DGX Spark) · 1,740 decisions
Cost: Estimate: $0.794 per 1,000 decisions (GPU time, at most). Counted as the wall clock from the first to the last answer, pauses over 10 min left out, × the hourly rate ÷ decisions. 6.5 h on NVIDIA DGX Spark (GB10) × $0.213/h = $1.38; total $1.38 ÷ 1,740 decisions; left out: 1 gaps over 10 min between consecutive answers, 32.5 h in all (each one listed in the data file). NVIDIA DGX Spark (GB10): CHF 4,000 ÷ (3 years × 8,760 h) = CHF 0.152/h purchase + CHF 0.2838/kWh (ewz.natur high rate) × 0.0791 kW (the chip's measured draw, not the whole box) = CHF 0.022/h electricity; CHF 0.175/h ≈ $0.213/h (CHF 1 = $1.2185, ECB 2026-11-10). Other setups' servers may have run on the same machine at the same time; each setup is charged the whole device, so this is an upper bound.
Parameters: 31.27B incl. its vision encoder; card: 31B (backbone gemma-4-31B-it; 29.29B trained) · dense
Size class by the maker's figure, 31B; our checkpoint count 31.27B.
Tier (same positions) not run yet
Did they improve? not in the learning plan
Qwen3.8-27B · Alibaba · chat model · low · NVIDIA RTX PRO 6000 Blackwell + NVIDIA DGX Spark
Risk judgement 62.0 (95%: 60.1–63.9)
Risks found 33.8% · safe right 90.2%
Took 242 of 715 risks that paid · played safe in 735 of 815 positions where safe paid
Error rate 29.0 (95%: 26.5–31.8) · record 9–0–9
League 2
$39.023 per 1,000 decisions$39.023 per 1M decisions (estimate · RTX PRO 6000 Blackwell + API) · 2,108 decisions
Cost: Estimate: $39.023 per 1,000 decisions (GPU time, at most). Counted as the wall clock from the first to the last answer, pauses over 10 min left out, × the hourly rate ÷ decisions. 5.0 h on NVIDIA DGX Spark (GB10) × $0.213/h = $1.07 + 32.6 h on NVIDIA RTX PRO 6000 Blackwell (96 GB) × $2.49/h = $81.19; plus 1 answers from the hosted API at their recorded cost, $0.00; total $82.26 ÷ 2,108 decisions; left out: 61 gaps over 10 min between consecutive answers, 122.0 h in all (each one listed in the data file). NVIDIA RTX PRO 6000 Blackwell (96 GB): $2.49/h per GPU. NVIDIA DGX Spark (GB10): CHF 4,000 ÷ (3 years × 8,760 h) = CHF 0.152/h purchase + CHF 0.2838/kWh (ewz.natur high rate) × 0.0791 kW (the chip's measured draw, not the whole box) = CHF 0.022/h electricity; CHF 0.175/h ≈ $0.213/h (CHF 1 = $1.2185, ECB 2026-11-10). Other setups' servers may have run on the same machine at the same time; each setup is charged the whole device, so this is an upper bound.
Parameters: 27.78B incl. its vision encoder; card: 27B · dense
Size class by the maker's figure, 27B; our checkpoint count 27.78B.
Tier (same positions) 2
Released Aug 2026
Did they improve? No · +19.0 pp · threshold 5.0 pp
Qwen3.8-27B · Alibaba · chat model · off · NVIDIA RTX PRO 6000 Blackwell + NVIDIA DGX Spark
Risk judgement 57.6 (95%: 56.1–59.0)
Risks found 23.5% · safe right 91.7%
Took 178 of 756 risks that paid · played safe in 671 of 732 positions where safe paid
Error rate 45.0 (95%: 40.7–49.9) · record 9–1–8
League 1
$4.551 per 1,000 decisions$4.551 per 1M decisions (estimate · RTX PRO 6000 Blackwell) · 2,005 decisions
Cost: Estimate: $4.551 per 1,000 decisions (GPU time, at most). Counted as the wall clock from the first to the last answer, pauses over 10 min left out, × the hourly rate ÷ decisions. 0.06 h on NVIDIA DGX Spark (GB10) × $0.213/h = $0.01 + 3.7 h on NVIDIA RTX PRO 6000 Blackwell (96 GB) × $2.49/h = $9.11; total $9.13 ÷ 2,005 decisions; left out: 6 gaps over 10 min between consecutive answers, 117.9 h in all (each one listed in the data file). NVIDIA RTX PRO 6000 Blackwell (96 GB): $2.49/h per GPU. NVIDIA DGX Spark (GB10): CHF 4,000 ÷ (3 years × 8,760 h) = CHF 0.152/h purchase + CHF 0.2838/kWh (ewz.natur high rate) × 0.0791 kW (the chip's measured draw, not the whole box) = CHF 0.022/h electricity; CHF 0.175/h ≈ $0.213/h (CHF 1 = $1.2185, ECB 2026-11-10). Other setups' servers may have run on the same machine at the same time; each setup is charged the whole device, so this is an upper bound.
Parameters: 27.78B incl. its vision encoder; card: 27B · dense
Size class by the maker's figure, 27B; our checkpoint count 27.78B.
Tier (same positions) not run yet
Released Aug 2026
Did they improve? not in the learning plan
GLM-5.3 · Z.ai · chat model · low
Risk judgement 61.7 (95%: 59.7–63.8)
Risks found 30.7% · safe right 92.7%
Took 205 of 668 risks that paid · played safe in 726 of 783 positions where safe paid
Error rate 30.9 (95%: 27.8–34.0) · record 7–0–11
League 2
$2.917 per 1,000 decisions$2.917 per 1M decisions (API price) · 1,989 decisions
Parameters: 753.33B MoE; active not disclosed by maker
The maker's model card states no total; 753.33B is counted from the released files (Hugging Face's file total agrees).
Tier (same positions) 1
Released Aug 2026
Did they improve? Yes · +17.6 pp · threshold 9.0 pp
KnowLine-31B-Gen1.5 · PelaAI · decision model · NVIDIA DGX Spark (GB10)
Risk judgement 61.6 (95%: 59.6–63.5)
Risks found 28.8% · safe right 94.4%
Took 187 of 649 risks that paid · played safe in 758 of 803 positions where safe paid
Error rate 26.2 (95%: 23.0–29.4) · record 13–1–3 · late entry
Played the original League 1 field after the league finished (late entry)
17 of 19 matches · GPT-6 LunaDecisions API: outside the requested scope (Ümit, 12 Nov); not played (opponent's API out of credit) · Mercury Decide: outside the requested scope (Ümit, 12 Nov); not played (opponent no longer served on OpenRouter)
1,928 decisions
Parameters: 31.27B incl. its vision encoder; card: about 31B · dense
Size class by the maker's figure, 31B; our checkpoint count 31.27B.
Tier (same positions) not run yet
Did they improve? not in the learning plan
REAX 1.3 · REAX · decision model · NVIDIA RTX PRO 6000 Blackwell
Risk judgement 60.5 (95%: 58.7–62.4)
Risks found 31.7% · safe right 89.4%
Took 211 of 666 risks that paid · played safe in 760 of 850 positions where safe paid
Error rate 27.8 (95%: 24.9–30.6) · record 11–1–6 · late entry
Played the original League 1 field after the league finished (late entry)
18 of 19 matches · GPT-6 LunaDecisions API: outside the requested scope (Ümit, 12 Nov); not played (opponent's API out of credit)
$1.545 per 1,000 decisions$1.545 per 1M decisions (estimate · RTX PRO 6000 Blackwell) · 1,998 decisions
Cost: Estimate: $1.545 per 1,000 decisions (GPU time, at most). Counted as the wall clock from the first to the last answer, pauses over 10 min left out, × the hourly rate ÷ decisions. 1.2 h on NVIDIA RTX PRO 6000 Blackwell (96 GB) × $2.49/h = $3.09; total $3.09 ÷ 1,998 decisions; left out: 2 gaps over 10 min between consecutive answers, 4.9 h in all (each one listed in the data file). NVIDIA RTX PRO 6000 Blackwell (96 GB): $2.49/h per GPU. Other setups' servers may have run on the same machine at the same time; each setup is charged the whole device, so this is an upper bound.
Parameters: part G 31.27B + part Q 26.09B (each incl. its vision encoder) + decision head 1.3M · dense
Two models run together, option probabilities averaged 50/50: 57.36B in all, all used on every question.
Tier (same positions) not run yet
Did they improve? (decision models, two arms) waiting (Ümit's D5 decision)
GLiDE · Fastino · decision model · API
Risk judgement 60.4 (95%: 58.3–62.6)
Risks found 36.9% · safe right 84.0%
Took 249 of 675 risks that paid · played safe in 756 of 900 positions where safe paid
Error rate 33.2 (95%: 30.2–36.4) · record 5–0–13
League 2
$0.153 per 1,000 decisions$0.153 per 1M decisions (API price) · 2,159 decisions
Cost: List price × our recorded tokens: 8,267,523 input tokens × $0.04 per 1M (output $0) = $0.33 ÷ 2,159 decisions (https://docs.fastino.ai/pricing)
Parameters: not disclosed by maker
Closed · Efficient ($0.04 per 1M input tokens, standard list price).
Tier (same positions) not run yet
Released Sep 2026
Did they improve? not in the learning plan
Turion Jev 31B · Turion.AI · decision model · NVIDIA DGX Spark (GB10)
Risk judgement 59.6 (95%: 57.7–61.4)
Risks found 24.0% · safe right 95.1%
Took 162 of 674 risks that paid · played safe in 680 of 715 positions where safe paid
Error rate 29.7 (95%: 26.5–33.3) · record 13–1–3 · late entry
Played the original League 1 field after the league finished (late entry)
17 of 19 matches · GPT-6 LunaDecisions API: outside the requested scope (Ümit, 12 Nov); not played (opponent's API out of credit) · Mercury Decide: outside the requested scope (Ümit, 12 Nov); not played (opponent no longer served on OpenRouter)
$0.293 per 1,000 decisions$0.293 per 1M decisions (estimate · DGX Spark) · 1,855 decisions
Cost: Estimate: $0.293 per 1,000 decisions (GPU time, at most). Counted as the wall clock from the first to the last answer, pauses over 10 min left out, × the hourly rate ÷ decisions. 2.6 h on NVIDIA DGX Spark (GB10) × $0.213/h = $0.54; total $0.54 ÷ 1,855 decisions; left out: 1 gaps over 10 min between consecutive answers, 14.6 h in all (each one listed in the data file). NVIDIA DGX Spark (GB10): CHF 4,000 ÷ (3 years × 8,760 h) = CHF 0.152/h purchase + CHF 0.2838/kWh (ewz.natur high rate) × 0.0791 kW (the chip's measured draw, not the whole box) = CHF 0.022/h electricity; CHF 0.175/h ≈ $0.213/h (CHF 1 = $1.2185, ECB 2026-11-10). Other setups' servers may have run on the same machine at the same time; each setup is charged the whole device, so this is an upper bound.
Parameters: 31.27B incl. its vision encoder; card: 31B (base gemma-4-31B-it) · dense
Size class by the maker's figure, 31B; our checkpoint count 31.27B.
Tier (same positions) not run yet
Did they improve? not in the learning plan
Jev 1.13 · TypeSafe · decision model
Risk judgement 59.5 (95%: 57.4–61.6)
Risks found 27.0% · safe right 92.1%
Took 190 of 705 risks that paid · played safe in 710 of 771 positions where safe paid
Error rate 34.4 (95%: 31.0–38.0) · record 12–0–6
League 1
$0.166 per 1,000 decisions$0.166 per 1M decisions (API price) · 1,911 decisions
Parameters: not disclosed by maker
Closed · Efficient ($0.042 per 1M input tokens, standard list price).
Tier (same positions) not run yet
Did they improve? not in the learning plan
Qwen3.8 Flash · Alibaba · chat model · off
Risk judgement 59.5 (95%: 57.2–61.7)
Risks found 34.4% · safe right 84.6%
Took 243 of 706 risks that paid · played safe in 613 of 725 positions where safe paid
Error rate 33.6 (95%: 30.8–36.7) · record 2–0–16
League 2
$0.284 per 1,000 decisions$0.284 per 1M decisions (API price) · 2,027 decisions
Parameters: not disclosed by maker
Closed · Efficient ($0.15 per 1M input tokens, standard list price).
Tier (same positions) 2
Did they improve? No · +2.7 pp · threshold 5.0 pp
Jev 1.14 · TypeSafe · decision model
Risk judgement 59.3 (95%: 57.1–61.4)
Risks found 29.1% · safe right 89.4%
Took 184 of 632 risks that paid · played safe in 657 of 735 positions where safe paid
Error rate 31.7 (95%: 28.3–35.7) · record 5–0–13
League 2
$0.173 per 1,000 decisions$0.173 per 1M decisions (API price) · 1,912 decisions
Parameters: not disclosed by maker
Closed · Efficient ($0.042 per 1M input tokens, standard list price).
Tier (same positions) not run yet
Released Oct 2026
Did they improve? (decision models, two arms) not tested (conservative context guard)
Drex Max v1.1 · Nace.AI · decision model
Risk judgement 59.1 (95%: 57.0–61.3)
Risks found 35.6% · safe right 82.5%
Took 250 of 702 risks that paid · played safe in 775 of 939 positions where safe paid
Error rate 30.9 (95%: 28.2–33.7) · record 12–2–4 · late entry
Played the original League 1 field after the league finished (late entry)
18 of 19 matches · GPT-6 LunaDecisions API: outside the requested scope (Ümit, 12 Nov); not played (opponent's API out of credit)
$0.265 per 1,000 decisions$0.265 per 1M decisions (list price; output not billed) · 2,154 decisions
Parameters: not disclosed by maker
Closed · Efficient ($0.03 per 1M input tokens, introductory price, the only one published); class provisional: Only its launch price is published: the models reference lists $0.03, and nace.ai/developers says 'Drex Max v1.1 cost is at its 50% launch price'; no regular price for v1.1 is printed (Drex MaxNVIDIA RTX PRO 6000 Blackwell's launch post gave $0.06 for the earlier model, not used).
Tier (same positions) 2
Did they improve? (decision models, two arms) notes: complete · worst: waiting (cash approval)
GLiDE · Fastino · decision model · v1.2 · NVIDIA RTX PRO 6000 Blackwell
Risk judgement 58.8 (95%: 56.7–60.8)
Risks found 33.0% · safe right 84.6%
Took 219 of 664 risks that paid · played safe in 698 of 825 positions where safe paid
Error rate 35.0 (95%: 31.6–39.0) · record 12–0–6
League 1
$10.301 per 1,000 decisions$10.301 per 1M decisions (estimate · RTX PRO 6000 Blackwell) · 2,003 decisions
Cost: Estimate: $10.301 per 1,000 decisions (GPU time, at most). Counted as the wall clock from the first to the last answer, pauses over 10 min left out, × the hourly rate ÷ decisions. 8.3 h on NVIDIA RTX PRO 6000 Blackwell (96 GB) × $2.49/h = $20.63; total $20.63 ÷ 2,003 decisions; left out: 26 gaps over 10 min between consecutive answers, 81.0 h in all (each one listed in the data file). NVIDIA RTX PRO 6000 Blackwell (96 GB): $2.49/h per GPU. Other setups' servers may have run on the same machine at the same time; each setup is charged the whole device, so this is an upper bound.
Parameters: backbone 26.09B incl. its vision encoder + decision head 1.3M · dense
Size class by the maker's figure, 27B; our checkpoint count 26.09B.
Tier (same positions) not run yet
Released Oct 2026
Did they improve? (decision models, two arms) notes: stopped (its budget cap was reached) · worst: complete
Drex 2.0 · Nace.AI · decision model · API
Risk judgement 58.1 (95%: 55.7–60.4)
Risks found 31.5% · safe right 84.8%
Took 220 of 699 risks that paid · played safe in 623 of 735 positions where safe paid
Error rate 38.4 (95%: 35.6–41.4) · record 10–0–8 · late entry
Played the original League 1 field after the league finished (late entry)
18 of 19 matches · GPT-6 LunaDecisions API: outside the requested scope (Ümit, 12 Nov); not played (opponent's API out of credit)
$0.258 per 1,000 decisions$0.258 per 1M decisions (list price (billed); output not billed) · 1,937 decisions
Parameters: 35.11B incl. a vision tower the card says is dropped on load; card: 35B; 3B active · MoE
Mixture of experts: 35B total, about 3B active per step (the maker's figures); our checkpoint count 35.11B.
Tier (same positions) not run yet
Did they improve? not in the learning plan
Drex 2.0 · Nace.AI · decision model · NVIDIA RTX PRO 6000 Blackwell
Risk judgement 53.0 (95%: 50.5–55.2)
Risks found 26.2% · safe right 79.7%
Took 189 of 720 risks that paid · played safe in 581 of 729 positions where safe paid
Error rate 42.9 (95%: 39.1–47.1) · record 7–0–11 · late entry
Played the original League 1 field after the league finished (late entry)
18 of 19 matches · GPT-6 LunaDecisions API: outside the requested scope (Ümit, 12 Nov); not played (opponent's API out of credit)
$0.782 per 1,000 decisions$0.782 per 1M decisions (estimate · RTX PRO 6000 Blackwell) · 1,993 decisions
Cost: Estimate: $0.782 per 1,000 decisions (GPU time, at most). Counted as the wall clock from the first to the last answer, pauses over 10 min left out, × the hourly rate ÷ decisions. 0.6 h on NVIDIA RTX PRO 6000 Blackwell (96 GB) × $2.49/h = $1.56; total $1.56 ÷ 1,993 decisions; no gap over 10 min. NVIDIA RTX PRO 6000 Blackwell (96 GB): $2.49/h per GPU. Other setups' servers may have run on the same machine at the same time; each setup is charged the whole device, so this is an upper bound.
Parameters: 35.11B incl. a vision tower the card says is dropped on load; card: 35B; 3B active · MoE
Mixture of experts: 35B total, about 3B active per step (the maker's figures); our checkpoint count 35.11B.
Tier (same positions) not run yet
Did they improve? not in the learning plan
Perplexity Decider 27B v1.2 · Perplexity · decision model · NVIDIA RTX PRO 6000 Blackwell
Risk judgement 57.9 (95%: 56.0–59.9)
Risks found 33.4% · safe right 82.5%
Took 244 of 731 risks that paid · played safe in 682 of 827 positions where safe paid
Error rate 36.9 (95%: 33.9–40.1) · record 12–0–6
League 1
$12.227 per 1,000 decisions$12.227 per 1M decisions (estimate · RTX PRO 6000 Blackwell) · 2,028 decisions
Cost: Estimate: $12.227 per 1,000 decisions (GPU time, at most). Counted as the wall clock from the first to the last answer, pauses over 10 min left out, × the hourly rate ÷ decisions. 10.0 h on NVIDIA RTX PRO 6000 Blackwell (96 GB) × $2.49/h = $24.80; total $24.80 ÷ 2,028 decisions; left out: 19 gaps over 10 min between consecutive answers, 131.1 h in all (each one listed in the data file). NVIDIA RTX PRO 6000 Blackwell (96 GB): $2.49/h per GPU. Other setups' servers may have run on the same machine at the same time; each setup is charged the whole device, so this is an upper bound.
Parameters: backbone 26.09B incl. its vision encoder + decision head 1.3M; changelog: 27B · dense
Size class by the maker's figure, 27B; our checkpoint count 26.09B.
Tier (same positions) not run yet
Released Oct 2026
Did they improve? (decision models, two arms) complete
celeris-1-decision · Celeris · decision model
Risk judgement 57.8 (95%: 55.9–59.7)
Risks found 23.9% · safe right 91.7%
Took 163 of 683 risks that paid · played safe in 749 of 817 positions where safe paid
Error rate 35.6 (95%: 32.0–39.4) · record 12–2–4
League 1
$0.150 per 1,000 decisions$0.150 per 1M decisions (API price) · 1,922 decisions
Parameters: not disclosed by maker
Closed · Efficient ($0.04 per 1M input tokens, standard list price).
Tier (same positions) not run yet
Released Oct 2026
Did they improve? not in the learning plan
Elephant-1 · Base Labs · decision model · NVIDIA RTX PRO 6000 Blackwell
Risk judgement 57.7 (95%: 55.8–59.6)
Risks found 28.4% · safe right 87.0%
Took 231 of 812 risks that paid · played safe in 682 of 784 positions where safe paid
Error rate 44.6 (95%: 40.3–48.9) · record 11–0–8 · late entry
Played the original League 1 field after the league finished (late entry)
$0.685 per 1,000 decisions$0.685 per 1M decisions (estimate · RTX PRO 6000 Blackwell) · 2,044 decisions
Cost: Estimate: $0.685 per 1,000 decisions (GPU time, at most). Counted as the wall clock from the first to the last answer, pauses over 10 min left out, × the hourly rate ÷ decisions. 0.6 h on NVIDIA RTX PRO 6000 Blackwell (96 GB) × $2.49/h = $1.40; total $1.40 ÷ 2,044 decisions; left out: 2 gaps over 10 min between consecutive answers, 1.0 h in all (each one listed in the data file). NVIDIA RTX PRO 6000 Blackwell (96 GB): $2.49/h per GPU. Other setups' servers may have run on the same machine at the same time; each setup is charged the whole device, so this is an upper bound.
Parameters: 9.41B incl. its vision encoder; card: 9B · dense
Size class by the maker's figure, 9B; our checkpoint count 9.41B.
Tier (same positions) not run yet
Did they improve? (decision models, two arms) notes: waiting (Ümit's D5 decision) · worst: complete
Clef · Cloudflare · decision model · NVIDIA RTX PRO 6000 Blackwell + NVIDIA DGX Spark
Risk judgement 57.5 (95%: 55.4–59.8)
Risks found 39.5% · safe right 75.6%
Took 263 of 666 risks that paid · played safe in 603 of 798 positions where safe paid
Error rate 36.5 (95%: 33.5–39.6) · record 2–0–16
League 2
$5.736 per 1,000 decisions$5.736 per 1M decisions (estimate · RTX PRO 6000 Blackwell) · 1,978 decisions
Cost: Estimate: $5.736 per 1,000 decisions (GPU time, at most). Counted as the wall clock from the first to the last answer, pauses over 10 min left out, × the hourly rate ÷ decisions. 1.6 h on NVIDIA DGX Spark (GB10) × $0.213/h = $0.34 + 4.4 h on NVIDIA RTX PRO 6000 Blackwell (96 GB) × $2.49/h = $11.01; total $11.35 ÷ 1,978 decisions; left out: 7 gaps over 10 min between consecutive answers, 243.2 h in all (each one listed in the data file). NVIDIA RTX PRO 6000 Blackwell (96 GB): $2.49/h per GPU. NVIDIA DGX Spark (GB10): CHF 4,000 ÷ (3 years × 8,760 h) = CHF 0.152/h purchase + CHF 0.2838/kWh (ewz.natur high rate) × 0.0791 kW (the chip's measured draw, not the whole box) = CHF 0.022/h electricity; CHF 0.175/h ≈ $0.213/h (CHF 1 = $1.2185, ECB 2026-11-10). Other setups' servers may have run on the same machine at the same time; each setup is charged the whole device, so this is an upper bound.
Parameters: backbone 27.36B incl. its vision encoder + joint head 128.1M; card: 27B · dense
Size class by the maker's figure, 27B; our checkpoint count 27.48B.
Tier (same positions) not run yet
Released Oct 2026
Did they improve? not in the learning plan
StartLux-Decision-v1.1-4B-Instant · StartLux · decision model · NVIDIA DGX Spark (GB10)
Risk judgement 57.2 (95%: 55.0–59.3)
Risks found 34.1% · safe right 80.4%
Took 265 of 777 risks that paid · played safe in 594 of 739 positions where safe paid
Error rate 40.1 (95%: 36.7–43.7) · record 10–0–7 · late entry
Played the original League 1 field after the league finished (late entry)
17 of 19 matches · GPT-6 LunaDecisions API: outside the requested scope (Ümit, 12 Nov); not played (opponent's API out of credit) · Mercury Decide: outside the requested scope (Ümit, 12 Nov); not played (opponent no longer served on OpenRouter)
$0.072 per 1,000 decisions$0.072 per 1M decisions (estimate · DGX Spark) · 1,989 decisions
Cost: Estimate: $0.072 per 1,000 decisions (GPU time, at most). Counted as the wall clock from the first to the last answer, pauses over 10 min left out, × the hourly rate ÷ decisions. 0.7 h on NVIDIA DGX Spark (GB10) × $0.213/h = $0.14; total $0.14 ÷ 1,989 decisions; left out: 1 gaps over 10 min between consecutive answers, 12.5 h in all (each one listed in the data file). NVIDIA DGX Spark (GB10): CHF 4,000 ÷ (3 years × 8,760 h) = CHF 0.152/h purchase + CHF 0.2838/kWh (ewz.natur high rate) × 0.0791 kW (the chip's measured draw, not the whole box) = CHF 0.022/h electricity; CHF 0.175/h ≈ $0.213/h (CHF 1 = $1.2185, ECB 2026-11-10). Other setups' servers may have run on the same machine at the same time; each setup is charged the whole device, so this is an upper bound.
Parameters: 4.66B incl. its vision encoder and MTP layer; card: 4B · dense
Size class by the maker's figure, 4B; our checkpoint count 4.66B.
Tier (same positions) not run yet
Did they improve? not in the learning plan
Cygnet · Blockbrain Labs · decision model · NVIDIA RTX PRO 6000 Blackwell + NVIDIA DGX Spark
Risk judgement 57.1 (95%: 55.3–58.8)
Risks found 27.3% · safe right 86.8%
Took 205 of 750 risks that paid · played safe in 685 of 789 positions where safe paid
Error rate 38.6 (95%: 35.4–41.9) · record 12–1–5
League 1
$11.168 per 1,000 decisions$11.168 per 1M decisions (estimate · RTX PRO 6000 Blackwell) · 2,016 decisions
Cost: Estimate: $11.168 per 1,000 decisions (GPU time, at most). Counted as the wall clock from the first to the last answer, pauses over 10 min left out, × the hourly rate ÷ decisions. 0.6 h on NVIDIA DGX Spark (GB10) × $0.213/h = $0.12 + 9.0 h on NVIDIA RTX PRO 6000 Blackwell (96 GB) × $2.49/h = $22.39; total $22.51 ÷ 2,016 decisions; left out: 19 gaps over 10 min between consecutive answers, 252.8 h in all (each one listed in the data file). NVIDIA RTX PRO 6000 Blackwell (96 GB): $2.49/h per GPU. NVIDIA DGX Spark (GB10): CHF 4,000 ÷ (3 years × 8,760 h) = CHF 0.152/h purchase + CHF 0.2838/kWh (ewz.natur high rate) × 0.0791 kW (the chip's measured draw, not the whole box) = CHF 0.022/h electricity; CHF 0.175/h ≈ $0.213/h (CHF 1 = $1.2185, ECB 2026-11-10). Other setups' servers may have run on the same machine at the same time; each setup is charged the whole device, so this is an upper bound.
Parameters: 11.96B incl. its vision encoder; card: 11.95B · dense
Size class by the maker's figure, 11.95B; our checkpoint count 11.96B.
Base model: Gemma 4 12B IT
Tier (same positions) not run yet
Did they improve? (decision models, two arms) waiting (its layer never sees the lessons)
Perplexity Decider 27B v1.1 · Perplexity · decision model · NVIDIA RTX PRO 6000 Blackwell + NVIDIA DGX Spark
Risk judgement 56.9 (95%: 54.9–58.8)
Risks found 33.1% · safe right 80.7%
Took 233 of 703 risks that paid · played safe in 682 of 845 positions where safe paid
Error rate 38.8 (95%: 35.3–42.5) · record 10–0–8
League 1
$6.593 per 1,000 decisions$6.593 per 1M decisions (estimate · RTX PRO 6000 Blackwell) · 2,052 decisions
Cost: Estimate: $6.593 per 1,000 decisions (GPU time, at most). Counted as the wall clock from the first to the last answer, pauses over 10 min left out, × the hourly rate ÷ decisions. 2.3 h on NVIDIA DGX Spark (GB10) × $0.213/h = $0.49 + 5.2 h on NVIDIA RTX PRO 6000 Blackwell (96 GB) × $2.49/h = $13.04; total $13.53 ÷ 2,052 decisions; left out: 34 gaps over 10 min between consecutive answers, 255.1 h in all (each one listed in the data file). NVIDIA RTX PRO 6000 Blackwell (96 GB): $2.49/h per GPU. NVIDIA DGX Spark (GB10): CHF 4,000 ÷ (3 years × 8,760 h) = CHF 0.152/h purchase + CHF 0.2838/kWh (ewz.natur high rate) × 0.0791 kW (the chip's measured draw, not the whole box) = CHF 0.022/h electricity; CHF 0.175/h ≈ $0.213/h (CHF 1 = $1.2185, ECB 2026-11-10). Other setups' servers may have run on the same machine at the same time; each setup is charged the whole device, so this is an upper bound.
Parameters: backbone 26.09B incl. its vision encoder + decision head 1.3M · dense
Size class by the maker's figure, 27B; our checkpoint count 26.09B.
Tier (same positions) not run yet
Released Oct 2026
Did they improve? not in the learning plan
SubQ Snap 1.1 · Subquadratic · decision model
Risk judgement 56.7 (95%: 54.8–58.6)
Risks found 38.6% · safe right 74.8%
Took 308 of 798 risks that paid · played safe in 750 of 1,003 positions where safe paid
Error rate 40.2 (95%: 36.7–43.8) · record 12–0–7 · late entry
Played the original League 1 field after the league finished (late entry)
This pair may be SubQ Snap 1.1 against itself: under the 'subq-snap-preview' name the API returned answers identical to SubQ Snap 1.1 (1,000 identical paired positions: letters and probabilities).
$0.150 per 1,000 decisions$0.150 per 1M decisions (API price (billed); output free) · 2,326 decisions
Parameters: not disclosed by maker
Closed · Efficient ($0.04 per 1M input tokens, standard list price).
Tier (same positions) 2
Did they improve? (decision models, two arms) complete
SubQ Snap Preview · Subquadratic · decision model
Risk judgement 56.5 (95%: 53.8–59.1)
Risks found 37.9% · safe right 75.1%
Took 297 of 783 risks that paid · played safe in 673 of 896 positions where safe paid
Error rate 43.9 (95%: 39.3–48.8) · record 12–1–5
League 1
$0.193 per 1,000 decisions$0.193 per 1M decisions (API price) · 2,200 decisions
Parameters: not disclosed by maker
Closed · Efficient ($0.05 per 1M input tokens, standard list price).
Tier (same positions) not run yet
Did they improve? not in the learning plan
Cerno 9B v1.2 · Apertix AI · decision model · NVIDIA DGX Spark (GB10)
Risk judgement 56.1 (95%: 53.9–58.2)
Risks found 39.2% · safe right 72.9%
Took 288 of 734 risks that paid · played safe in 625 of 857 positions where safe paid
Error rate 48.5 (95%: 44.5–52.6) · record 6–1–10 · late entry
Played the original League 1 field after the league finished (late entry)
17 of 19 matches · GPT-6 LunaDecisions API: outside the requested scope (Ümit, 12 Nov); not played (opponent's API out of credit) · Mercury Decide: outside the requested scope (Ümit, 12 Nov); not played (opponent no longer served on OpenRouter)
$0.139 per 1,000 decisions$0.139 per 1M decisions (estimate · DGX Spark) · 2,108 decisions
Cost: Estimate: $0.139 per 1,000 decisions (GPU time, at most). Counted as the wall clock from the first to the last answer, pauses over 10 min left out, × the hourly rate ÷ decisions. 1.4 h on NVIDIA DGX Spark (GB10) × $0.213/h = $0.29; total $0.29 ÷ 2,108 decisions; left out: 1 gaps over 10 min between consecutive answers, 11.5 h in all (each one listed in the data file). NVIDIA DGX Spark (GB10): CHF 4,000 ÷ (3 years × 8,760 h) = CHF 0.152/h purchase + CHF 0.2838/kWh (ewz.natur high rate) × 0.0791 kW (the chip's measured draw, not the whole box) = CHF 0.022/h electricity; CHF 0.175/h ≈ $0.213/h (CHF 1 = $1.2185, ECB 2026-11-10). Other setups' servers may have run on the same machine at the same time; each setup is charged the whole device, so this is an upper bound.
Parameters: 8.95B (untied lm_head); card: 9B · dense
Size class by the maker's figure, 9B; our checkpoint count 8.95B.
Tier (same positions) not run yet
Did they improve? not in the learning plan
GPT-6 Luna · OpenAI · decision model · Decisions API
Risk judgement 55.7 (95%: 53.8–57.6)
Risks found 21.6% · safe right 89.7%
Took 160 of 740 risks that paid · played safe in 636 of 709 positions where safe paid
Error rate 43.3 (95%: 39.7–46.9) · record 11–1–6
League 1
$0.335 per 1,000 decisions$0.335 per 1M decisions (API price) · 1,962 decisions
Parameters: not disclosed by maker
Closed · Efficient ($0.1 per 1M input tokens, standard list price).
Tier (same positions) not run yet
Released Sep 2026
Did they improve? not in the learning plan
d1-2B · Liquid AI · decision model · NVIDIA RTX PRO 6000 Blackwell
Risk judgement 55.2 (95%: 52.8–57.5)
Risks found 33.6% · safe right 76.8%
Took 231 of 688 risks that paid · played safe in 596 of 776 positions where safe paid
Error rate 47.1 (95%: 42.8–51.5) · record 5–0–12 · late entry
Played the original League 1 field after the league finished (late entry)
17 of 19 matches · GPT-6 LunaDecisions API: outside the requested scope (Ümit, 12 Nov); not played (opponent's API out of credit) · Mercury Decide: outside the requested scope (Ümit, 12 Nov); not played (opponent no longer served on OpenRouter)
$0.467 per 1,000 decisions$0.467 per 1M decisions (estimate · RTX PRO 6000 Blackwell) · 1,980 decisions
Cost: Estimate: $0.467 per 1,000 decisions (GPU time, at most). Counted as the wall clock from the first to the last answer, pauses over 10 min left out, × the hourly rate ÷ decisions. 0.4 h on NVIDIA RTX PRO 6000 Blackwell (96 GB) × $2.49/h = $0.93; total $0.93 ÷ 1,980 decisions; left out: 1 gaps over 10 min between consecutive answers, 2.5 h in all (each one listed in the data file). NVIDIA RTX PRO 6000 Blackwell (96 GB): $2.49/h per GPU. Other setups' servers may have run on the same machine at the same time; each setup is charged the whole device, so this is an upper bound.
Parameters: 1.92B incl. its vision tower; card: 1.92B · dense
Size class by the maker's figure, 1.92B.
Base model: LFM3-VL-2B
Tier (same positions) not run yet
Did they improve? (decision models, two arms) not started (no backgammon route yet; no league record)
Winnow-12B · EldanRing · decision model · NVIDIA RTX PRO 6000 Blackwell
Risk judgement 55.2 (95%: 52.9–57.2)
Risks found 33.7% · safe right 76.6%
Took 263 of 780 risks that paid · played safe in 573 of 748 positions where safe paid
Error rate 49.7 (95%: 45.9–53.6) · record 7–0–11
League 1
$9.615 per 1,000 decisions$9.615 per 1M decisions (estimate · RTX PRO 6000 Blackwell) · 2,015 decisions
Cost: Estimate: $9.615 per 1,000 decisions (GPU time, at most). Counted as the wall clock from the first to the last answer, pauses over 10 min left out, × the hourly rate ÷ decisions. 7.8 h on NVIDIA RTX PRO 6000 Blackwell (96 GB) × $2.49/h = $19.37; total $19.37 ÷ 2,015 decisions; left out: 22 gaps over 10 min between consecutive answers, 149.6 h in all (each one listed in the data file). NVIDIA RTX PRO 6000 Blackwell (96 GB): $2.49/h per GPU. Other setups' servers may have run on the same machine at the same time; each setup is charged the whole device, so this is an upper bound.
Parameters: 11.91B dense
Size class by the maker's figure, 11.95B; our checkpoint count 11.91B.
Tier (same positions) not run yet
Did they improve? (decision models, two arms) notes: waiting (cash approval) · worst: waiting (its render check)
StartLux-Decision-v1.1-2B-Instant · StartLux · decision model · NVIDIA DGX Spark (GB10)
Risk judgement 53.8 (95%: 51.3–56.6)
Risks found 33.7% · safe right 74.0%
Took 212 of 630 risks that paid · played safe in 450 of 608 positions where safe paid
Error rate 50.0 (95%: 45.4–54.8) · record 3–0–14 · late entry
Played the original League 1 field after the league finished (late entry)
17 of 19 matches · GPT-6 LunaDecisions API: outside the requested scope (Ümit, 12 Nov); not played (opponent's API out of credit) · Mercury Decide: outside the requested scope (Ümit, 12 Nov); not played (opponent no longer served on OpenRouter)
$0.052 per 1,000 decisions$0.052 per 1M decisions (estimate · DGX Spark) · 1,771 decisions
Cost: Estimate: $0.052 per 1,000 decisions (GPU time, at most). Counted as the wall clock from the first to the last answer, pauses over 10 min left out, × the hourly rate ÷ decisions. 0.4 h on NVIDIA DGX Spark (GB10) × $0.213/h = $0.09; total $0.09 ÷ 1,771 decisions; left out: 1 gaps over 10 min between consecutive answers, 63.8 h in all (each one listed in the data file). NVIDIA DGX Spark (GB10): CHF 4,000 ÷ (3 years × 8,760 h) = CHF 0.152/h purchase + CHF 0.2838/kWh (ewz.natur high rate) × 0.0791 kW (the chip's measured draw, not the whole box) = CHF 0.022/h electricity; CHF 0.175/h ≈ $0.213/h (CHF 1 = $1.2185, ECB 2026-11-10). Other setups' servers may have run on the same machine at the same time; each setup is charged the whole device, so this is an upper bound.
Parameters: 2.27B incl. its vision encoder and MTP layer; card: 2B · dense
Size class by the maker's figure, 2B; our checkpoint count 2.27B.
Tier (same positions) not run yet
Did they improve? (decision models, two arms) notes: waiting (cash approval) · worst: waiting (its render check)
Mercury Decide · Inception · decision model
Risk judgement 53.4 (95%: 51.5–55.2)
Risks found 18.7% · safe right 88.1%
Took 129 of 690 risks that paid · played safe in 583 of 662 positions where safe paid
Error rate 47.9 (95%: 43.3–52.9) · record 8–1–9
League 1
$0.071 per 1,000 decisions$0.071 per 1M decisions (API price) · 1,853 decisions
Parameters: not disclosed by maker
Closed · Efficient ($0.04 per 1M input tokens, standard list price).
Tier (same positions) not run yet
Did they improve? not in the learning plan
d1-Omni-2B · Liquid AI · decision model · NVIDIA RTX PRO 6000 Blackwell
Risk judgement 53.2 (95%: 50.9–55.6)
Risks found 30.4% · safe right 76.0%
Took 188 of 619 risks that paid · played safe in 553 of 728 positions where safe paid
Error rate 49.8 (95%: 43.5–57.4) · record 9–0–8 · late entry
Played the original League 1 field after the league finished (late entry)
17 of 19 matches · GPT-6 LunaDecisions API: outside the requested scope (Ümit, 12 Nov); not played (opponent's API out of credit) · Mercury Decide: outside the requested scope (Ümit, 12 Nov); not played (opponent no longer served on OpenRouter)
$0.657 per 1,000 decisions$0.657 per 1M decisions (estimate · RTX PRO 6000 Blackwell) · 1,710 decisions
Cost: Estimate: $0.657 per 1,000 decisions (GPU time, at most). Counted as the wall clock from the first to the last answer, pauses over 10 min left out, × the hourly rate ÷ decisions. 0.5 h on NVIDIA RTX PRO 6000 Blackwell (96 GB) × $2.49/h = $1.12; total $1.12 ÷ 1,710 decisions; no gap over 10 min. NVIDIA RTX PRO 6000 Blackwell (96 GB): $2.49/h per GPU. Other setups' servers may have run on the same machine at the same time; each setup is charged the whole device, so this is an upper bound.
Parameters: 2.17B incl. its vision and audio parts; card: 2.17B · dense
Size class by the maker's figure, 2.17B.
Base model: LFM3-Omni-2B
Tier (same positions) not run yet
Did they improve? not in the learning plan
LFM2.5-24B-A2B · Liquid AI · chat model · on · NVIDIA RTX PRO 6000 Blackwell + NVIDIA DGX Spark
Risk judgement 52.4 (95%: 50.3–54.5)
Risks found 31.5% · safe right 73.4%
Took 248 of 788 risks that paid · played safe in 647 of 882 positions where safe paid
Error rate 47.7 (95%: 44.1–51.2) · record 10–0–8
League 1
$38.716 per 1,000 decisions$38.716 per 1M decisions (estimate · RTX PRO 6000 Blackwell) · 2,193 decisions
Cost: Estimate: $38.716 per 1,000 decisions (GPU time, at most). Counted as the wall clock from the first to the last answer, pauses over 10 min left out, × the hourly rate ÷ decisions. 0.1 h on NVIDIA DGX Spark (GB10) × $0.213/h = $0.02 + 34.1 h on NVIDIA RTX PRO 6000 Blackwell (96 GB) × $2.49/h = $84.88; total $84.90 ÷ 2,193 decisions; left out: 16 gaps over 10 min between consecutive answers, 97.1 h in all (each one listed in the data file). NVIDIA RTX PRO 6000 Blackwell (96 GB): $2.49/h per GPU. NVIDIA DGX Spark (GB10): CHF 4,000 ÷ (3 years × 8,760 h) = CHF 0.152/h purchase + CHF 0.2838/kWh (ewz.natur high rate) × 0.0791 kW (the chip's measured draw, not the whole box) = CHF 0.022/h electricity; CHF 0.175/h ≈ $0.213/h (CHF 1 = $1.2185, ECB 2026-11-10). Other setups' servers may have run on the same machine at the same time; each setup is charged the whole device, so this is an upper bound.
Parameters: 23.97B MoE · 2.45B active
Mixture of experts: 24B total, about 2.45B active per step (the maker's figures); our checkpoint count 23.97B.
Tier (same positions) not run yet
Released Oct 2026
Did they improve? pending
LFM2.5-24B-A2B · Liquid AI · chat model · off · NVIDIA RTX PRO 6000 Blackwell
Risk judgement 45.7 (95%: 43.2–48.1)
Risks found 28.8% · safe right 62.7%
Took 206 of 715 risks that paid · played safe in 470 of 750 positions where safe paid
Error rate 61.5 (95%: 56.3–66.8) · record 3–0–15
League 1
$9.132 per 1,000 decisions$9.132 per 1M decisions (estimate · RTX PRO 6000 Blackwell) · 1,952 decisions
Cost: Estimate: $9.132 per 1,000 decisions (GPU time, at most). Counted as the wall clock from the first to the last answer, pauses over 10 min left out, × the hourly rate ÷ decisions. 7.2 h on NVIDIA RTX PRO 6000 Blackwell (96 GB) × $2.49/h = $17.83; total $17.83 ÷ 1,952 decisions; left out: 19 gaps over 10 min between consecutive answers, 87.9 h in all (each one listed in the data file). NVIDIA RTX PRO 6000 Blackwell (96 GB): $2.49/h per GPU. Other setups' servers may have run on the same machine at the same time; each setup is charged the whole device, so this is an upper bound.
Parameters: 23.97B MoE · 2.45B active
Mixture of experts: 24B total, about 2.45B active per step (the maker's figures); our checkpoint count 23.97B.
Tier (same positions) not run yet
Released Oct 2026
Did they improve? not in the learning plan
KnowLine-2B-Gen1 · PelaAI · decision model · NVIDIA DGX Spark (GB10)
Risk judgement 51.1 (95%: 48.7–53.5)
Risks found 30.0% · safe right 72.3%
Took 203 of 676 risks that paid · played safe in 508 of 703 positions where safe paid
Error rate 54.5 (95%: 48.9–60.8) · record 3–0–14 · late entry
Played the original League 1 field after the league finished (late entry)
17 of 19 matches · GPT-6 LunaDecisions API: outside the requested scope (Ümit, 12 Nov); not played (opponent's API out of credit) · Mercury Decide: outside the requested scope (Ümit, 12 Nov); not played (opponent no longer served on OpenRouter)
$0.049 per 1,000 decisions$0.049 per 1M decisions (estimate · DGX Spark) · 1,955 decisions
Cost: Estimate: $0.049 per 1,000 decisions (GPU time, at most). Counted as the wall clock from the first to the last answer, pauses over 10 min left out, × the hourly rate ÷ decisions. 0.5 h on NVIDIA DGX Spark (GB10) × $0.213/h = $0.10; total $0.10 ÷ 1,955 decisions; left out: 1 gaps over 10 min between consecutive answers, 34.0 h in all (each one listed in the data file). NVIDIA DGX Spark (GB10): CHF 4,000 ÷ (3 years × 8,760 h) = CHF 0.152/h purchase + CHF 0.2838/kWh (ewz.natur high rate) × 0.0791 kW (the chip's measured draw, not the whole box) = CHF 0.022/h electricity; CHF 0.175/h ≈ $0.213/h (CHF 1 = $1.2185, ECB 2026-11-10). Other setups' servers may have run on the same machine at the same time; each setup is charged the whole device, so this is an upper bound.
Parameters: 2.27B incl. its vision encoder and MTP layer; card: 2B · dense
Size class by the maker's figure, 2B; our checkpoint count 2.27B.
Base model: Qwen3.5-2B
Tier (same positions) not run yet
Did they improve? (decision models, two arms) notes: waiting (cash approval) · worst: waiting (its render check)
KnowLine 4B Gen5.5 · PelaAI · decision model · NVIDIA DGX Spark (GB10)
Risk judgement 49.7 (95%: 47.0–52.3)
Risks found 34.1% · safe right 65.4%
Took 265 of 778 risks that paid · played safe in 532 of 813 positions where safe paid
Error rate 53.6 (95%: 48.8–58.6) · record 5–1–11 · late entry
Played the original League 1 field after the league finished (late entry)
17 of 19 matches · GPT-6 LunaDecisions API: outside the requested scope (Ümit, 12 Nov); not played (opponent's API out of credit) · Mercury Decide: outside the requested scope (Ümit, 12 Nov); not played (opponent no longer served on OpenRouter)
$0.054 per 1,000 decisions$0.054 per 1M decisions (estimate · DGX Spark) · 2,153 decisions
Cost: Estimate: $0.054 per 1,000 decisions (GPU time, at most). Counted as the wall clock from the first to the last answer, pauses over 10 min left out, × the hourly rate ÷ decisions. 0.5 h on NVIDIA DGX Spark (GB10) × $0.213/h = $0.12; total $0.12 ÷ 2,153 decisions; left out: 1 gaps over 10 min between consecutive answers, 64.1 h in all (each one listed in the data file). NVIDIA DGX Spark (GB10): CHF 4,000 ÷ (3 years × 8,760 h) = CHF 0.152/h purchase + CHF 0.2838/kWh (ewz.natur high rate) × 0.0791 kW (the chip's measured draw, not the whole box) = CHF 0.022/h electricity; CHF 0.175/h ≈ $0.213/h (CHF 1 = $1.2185, ECB 2026-11-10). Other setups' servers may have run on the same machine at the same time; each setup is charged the whole device, so this is an upper bound.
Parameters: 4.66B incl. its vision encoder and MTP layer; card: 4B · dense
Size class by the maker's figure, 4B; our checkpoint count 4.66B.
Tier (same positions) not run yet
Did they improve? (decision models, two arms) notes: waiting (cash approval) · worst: waiting (its render check)
Perplexity Decider Flash v1.2 · Perplexity · decision model · NVIDIA RTX PRO 6000 Blackwell
Risk judgement 49.1 (95%: 46.5–51.6)
Risks found 31.3% · safe right 66.9%
Took 223 of 712 risks that paid · played safe in 519 of 776 positions where safe paid
Error rate 59.6 (95%: 54.9–64.5) · record 2–0–16
League 1
$12.267 per 1,000 decisions$12.267 per 1M decisions (estimate · RTX PRO 6000 Blackwell) · 2,006 decisions
Cost: Estimate: $12.267 per 1,000 decisions (GPU time, at most). Counted as the wall clock from the first to the last answer, pauses over 10 min left out, × the hourly rate ÷ decisions. 9.9 h on NVIDIA RTX PRO 6000 Blackwell (96 GB) × $2.49/h = $24.61; total $24.61 ÷ 2,006 decisions; left out: 22 gaps over 10 min between consecutive answers, 147.3 h in all (each one listed in the data file). NVIDIA RTX PRO 6000 Blackwell (96 GB): $2.49/h per GPU. Other setups' servers may have run on the same machine at the same time; each setup is charged the whole device, so this is an upper bound.
Parameters: backbone 4.54B incl. its vision encoder + decision head 0.7M; changelog: 4B · dense
Size class by the maker's figure, 4B; our checkpoint count 4.54B.
Tier (same positions) not run yet
Released Oct 2026
Did they improve? (decision models, two arms) notes: waiting (cash approval) · worst: waiting (its render check)
Open-Jev-27B-v1.1 · Zefan Cai · decision model · NVIDIA RTX PRO 6000 Blackwell
Risk judgement 48.5 (95%: 46.1–50.9)
Risks found 37.3% · safe right 59.8%
Took 264 of 708 risks that paid · played safe in 455 of 761 positions where safe paid
Error rate 65.6 (95%: 59.7–71.9) · record 2–1–15
League 1
$7.185 per 1,000 decisions$7.185 per 1M decisions (estimate · RTX PRO 6000 Blackwell) · 2,002 decisions
Cost: Estimate: $7.185 per 1,000 decisions (GPU time, at most). Counted as the wall clock from the first to the last answer, pauses over 10 min left out, × the hourly rate ÷ decisions. 5.8 h on NVIDIA RTX PRO 6000 Blackwell (96 GB) × $2.49/h = $14.38; total $14.38 ÷ 2,002 decisions; left out: 13 gaps over 10 min between consecutive answers, 257.6 h in all (each one listed in the data file). NVIDIA RTX PRO 6000 Blackwell (96 GB): $2.49/h per GPU. Other setups' servers may have run on the same machine at the same time; each setup is charged the whole device, so this is an upper bound.
Parameters: 27.80B: Qwen3.8-27B base 27.78B + adapter and head 15.47M (the repo holds only the adapter and head) · dense
Size class by the maker's figure, 27B; our checkpoint count 27.8B.
Base model: Qwen3.8-27B + adapter
Tier (same positions) not run yet
Did they improve? not in the learning plan
GLiDE 2B · Fastino · decision model · NVIDIA DGX Spark (GB10)
Risk judgement 46.7 (95%: 43.6–49.6)
Risks found 33.0% · safe right 60.3%
Took 192 of 581 risks that paid · played safe in 354 of 587 positions where safe paid
Error rate 67.4 (95%: 61.0–74.5) · record 1–0–16 · late entry
Played the original League 1 field after the league finished (late entry)
17 of 19 matches · GPT-6 LunaDecisions API: outside the requested scope (Ümit, 12 Nov); not played (opponent's API out of credit) · Mercury Decide: outside the requested scope (Ümit, 12 Nov); not played (opponent no longer served on OpenRouter)
$0.058 per 1,000 decisions$0.058 per 1M decisions (estimate · DGX Spark) · 1,676 decisions
Cost: Estimate: $0.058 per 1,000 decisions (GPU time, at most). Counted as the wall clock from the first to the last answer, pauses over 10 min left out, × the hourly rate ÷ decisions. 0.5 h on NVIDIA DGX Spark (GB10) × $0.213/h = $0.10; total $0.10 ÷ 1,676 decisions; left out: 1 gaps over 10 min between consecutive answers, 30.9 h in all (each one listed in the data file). NVIDIA DGX Spark (GB10): CHF 4,000 ÷ (3 years × 8,760 h) = CHF 0.152/h purchase + CHF 0.2838/kWh (ewz.natur high rate) × 0.0791 kW (the chip's measured draw, not the whole box) = CHF 0.022/h electricity; CHF 0.175/h ≈ $0.213/h (CHF 1 = $1.2185, ECB 2026-11-10). Other setups' servers may have run on the same machine at the same time; each setup is charged the whole device, so this is an upper bound.
Parameters: 1.88B incl. its decision readout; card: 1.88B · dense
Size class by the maker's figure, 1.88B.
Tier (same positions) not run yet
Did they improve? (decision models, two arms) notes: waiting (cash approval) · worst: waiting (its render check)
KnowLine-0.8B-Gen1 · PelaAI · decision model · NVIDIA DGX Spark (GB10)
Risk judgement 45.2 (95%: 42.5–47.7)
Risks found 30.8% · safe right 59.6%
Took 196 of 637 risks that paid · played safe in 354 of 594 positions where safe paid
Error rate 71.9 (95%: 66.2–77.9) · record 1–1–15 · late entry
Played the original League 1 field after the league finished (late entry)
17 of 19 matches · GPT-6 LunaDecisions API: outside the requested scope (Ümit, 12 Nov); not played (opponent's API out of credit) · Mercury Decide: outside the requested scope (Ümit, 12 Nov); not played (opponent no longer served on OpenRouter)
$0.049 per 1,000 decisions$0.049 per 1M decisions (estimate · DGX Spark) · 1,728 decisions
Cost: Estimate: $0.049 per 1,000 decisions (GPU time, at most). Counted as the wall clock from the first to the last answer, pauses over 10 min left out, × the hourly rate ÷ decisions. 0.4 h on NVIDIA DGX Spark (GB10) × $0.213/h = $0.08; total $0.08 ÷ 1,728 decisions; left out: 1 gaps over 10 min between consecutive answers, 55.0 h in all (each one listed in the data file). NVIDIA DGX Spark (GB10): CHF 4,000 ÷ (3 years × 8,760 h) = CHF 0.152/h purchase + CHF 0.2838/kWh (ewz.natur high rate) × 0.0791 kW (the chip's measured draw, not the whole box) = CHF 0.022/h electricity; CHF 0.175/h ≈ $0.213/h (CHF 1 = $1.2185, ECB 2026-11-10). Other setups' servers may have run on the same machine at the same time; each setup is charged the whole device, so this is an upper bound.
Parameters: 0.87B incl. its vision encoder and MTP layer; card: 0.8B · dense
Size class by the maker's figure, 0.8B; our checkpoint count 0.87B.
Base model: Qwen3.5-0.8B
Tier (same positions) not run yet
Did they improve? (decision models, two arms) notes: waiting (cash approval) · worst: waiting (its render check)
StartLux-Decision-v1.1-0.8B-Instant · StartLux · decision model · NVIDIA DGX Spark (GB10)
Risk judgement 44.6 (95%: 42.3–46.9)
Risks found 38.3% · safe right 50.9%
Took 255 of 665 risks that paid · played safe in 364 of 715 positions where safe paid
Error rate 64.7 (95%: 59.3–70.3) · record 3–0–14 · late entry
Played the original League 1 field after the league finished (late entry)
17 of 19 matches · GPT-6 LunaDecisions API: outside the requested scope (Ümit, 12 Nov); not played (opponent's API out of credit) · Mercury Decide: outside the requested scope (Ümit, 12 Nov); not played (opponent no longer served on OpenRouter)
$0.054 per 1,000 decisions$0.054 per 1M decisions (estimate · DGX Spark) · 1,882 decisions
Cost: Estimate: $0.054 per 1,000 decisions (GPU time, at most). Counted as the wall clock from the first to the last answer, pauses over 10 min left out, × the hourly rate ÷ decisions. 0.5 h on NVIDIA DGX Spark (GB10) × $0.213/h = $0.10; total $0.10 ÷ 1,882 decisions; left out: 1 gaps over 10 min between consecutive answers, 54.0 h in all (each one listed in the data file). NVIDIA DGX Spark (GB10): CHF 4,000 ÷ (3 years × 8,760 h) = CHF 0.152/h purchase + CHF 0.2838/kWh (ewz.natur high rate) × 0.0791 kW (the chip's measured draw, not the whole box) = CHF 0.022/h electricity; CHF 0.175/h ≈ $0.213/h (CHF 1 = $1.2185, ECB 2026-11-10). Other setups' servers may have run on the same machine at the same time; each setup is charged the whole device, so this is an upper bound.
Parameters: 0.87B incl. its vision encoder and MTP layer; card: 0.8B · dense
Size class by the maker's figure, 0.8B; our checkpoint count 0.87B.
Base model: Qwen3.5-0.8B
Tier (same positions) not run yet
Did they improve? (decision models, two arms) notes: waiting (cash approval) · worst: waiting (its render check)
OneJev1.6-0.8B · OmniJev · decision model · NVIDIA DGX Spark (GB10)
Risk judgement 42.5 (95%: 39.3–45.8)
Risks found 27.6% · safe right 57.4%
Took 167 of 606 risks that paid · played safe in 364 of 634 positions where safe paid
Error rate 82.5 (95%: 75.2–90.8) · record 0–0–17 · late entry
Played the original League 1 field after the league finished (late entry)
17 of 19 matches · GPT-6 LunaDecisions API: outside the requested scope (Ümit, 12 Nov); not played (opponent's API out of credit) · Mercury Decide: outside the requested scope (Ümit, 12 Nov); not played (opponent no longer served on OpenRouter)
$0.052 per 1,000 decisions$0.052 per 1M decisions (estimate · DGX Spark) · 1,763 decisions
Cost: Estimate: $0.052 per 1,000 decisions (GPU time, at most). Counted as the wall clock from the first to the last answer, pauses over 10 min left out, × the hourly rate ÷ decisions. 0.4 h on NVIDIA DGX Spark (GB10) × $0.213/h = $0.09; total $0.09 ÷ 1,763 decisions; left out: 1 gaps over 10 min between consecutive answers, 53.0 h in all (each one listed in the data file). NVIDIA DGX Spark (GB10): CHF 4,000 ÷ (3 years × 8,760 h) = CHF 0.152/h purchase + CHF 0.2838/kWh (ewz.natur high rate) × 0.0791 kW (the chip's measured draw, not the whole box) = CHF 0.022/h electricity; CHF 0.175/h ≈ $0.213/h (CHF 1 = $1.2185, ECB 2026-11-10). Other setups' servers may have run on the same machine at the same time; each setup is charged the whole device, so this is an upper bound.
Parameters: 0.85B incl. its vision encoder; card: 0.9B · dense
Size class by the maker's figure, 0.9B; our checkpoint count 0.85B.
Tier (same positions) not run yet
Did they improve? (decision models, two arms) notes: waiting (cash approval) · worst: waiting (its render check)
GLiDE 0.8B · Fastino · decision model · NVIDIA DGX Spark (GB10)
Risk judgement 41.7 (95%: 38.9–44.3)
Risks found 30.4% · safe right 53.1%
Took 204 of 671 risks that paid · played safe in 352 of 663 positions where safe paid
Error rate 80.4 (95%: 71.8–89.3) · record 2–1–14 · late entry
Played the original League 1 field after the league finished (late entry)
17 of 19 matches · GPT-6 LunaDecisions API: outside the requested scope (Ümit, 12 Nov); not played (opponent's API out of credit) · Mercury Decide: outside the requested scope (Ümit, 12 Nov); not played (opponent no longer served on OpenRouter)
$0.051 per 1,000 decisions$0.051 per 1M decisions (estimate · DGX Spark) · 1,832 decisions
Cost: Estimate: $0.051 per 1,000 decisions (GPU time, at most). Counted as the wall clock from the first to the last answer, pauses over 10 min left out, × the hourly rate ÷ decisions. 0.4 h on NVIDIA DGX Spark (GB10) × $0.213/h = $0.09; total $0.09 ÷ 1,832 decisions; left out: 1 gaps over 10 min between consecutive answers, 31.4 h in all (each one listed in the data file). NVIDIA DGX Spark (GB10): CHF 4,000 ÷ (3 years × 8,760 h) = CHF 0.152/h purchase + CHF 0.2838/kWh (ewz.natur high rate) × 0.0791 kW (the chip's measured draw, not the whole box) = CHF 0.022/h electricity; CHF 0.175/h ≈ $0.213/h (CHF 1 = $1.2185, ECB 2026-11-10). Other setups' servers may have run on the same machine at the same time; each setup is charged the whole device, so this is an upper bound.
Parameters: 0.75B incl. its decision readout; card: 0.75B · dense
Size class by the maker's figure, 0.75B.
Tier (same positions) not run yet
Did they improve? (decision models, two arms) notes: waiting (cash approval) · worst: waiting (its render check)
GLiDE 0.4B · Fastino · decision model · NVIDIA DGX Spark (GB10)
Risk judgement 28.9 (95%: 25.6–32.1)
Risks found 18.8% · safe right 39.0%
Took 83 of 441 risks that paid · played safe in 194 of 498 positions where safe paid
Error rate 113.2 (95%: 102.1–124.1) · record 1–0–16 · late entry
Played the original League 1 field after the league finished (late entry)
17 of 19 matches · GPT-6 LunaDecisions API: outside the requested scope (Ümit, 12 Nov); not played (opponent's API out of credit) · Mercury Decide: outside the requested scope (Ümit, 12 Nov); not played (opponent no longer served on OpenRouter)
$0.057 per 1,000 decisions$0.057 per 1M decisions (estimate · DGX Spark) · 1,355 decisions
Cost: Estimate: $0.057 per 1,000 decisions (GPU time, at most). Counted as the wall clock from the first to the last answer, pauses over 10 min left out, × the hourly rate ÷ decisions. 0.4 h on NVIDIA DGX Spark (GB10) × $0.213/h = $0.08; total $0.08 ÷ 1,355 decisions; left out: 1 gaps over 10 min between consecutive answers, 31.7 h in all (each one listed in the data file). NVIDIA DGX Spark (GB10): CHF 4,000 ÷ (3 years × 8,760 h) = CHF 0.152/h purchase + CHF 0.2838/kWh (ewz.natur high rate) × 0.0791 kW (the chip's measured draw, not the whole box) = CHF 0.022/h electricity; CHF 0.175/h ≈ $0.213/h (CHF 1 = $1.2185, ECB 2026-11-10). Other setups' servers may have run on the same machine at the same time; each setup is charged the whole device, so this is an upper bound.
Parameters: 0.40B incl. its decision readout; card: 0.4B · dense
Size class by the maker's figure, 0.4B.
Tier (same positions) not run yet
Did they improve? (decision models, two arms) notes: waiting (cash approval) · worst: waiting (its render check)
GLiClass v4 Edge · Knowledgator · decision model · NVIDIA DGX Spark (GB10)
Risk judgement 21.5 (95%: 18.6–24.6)
Risks found 26.8% · safe right 16.3%
Took 136 of 508 risks that paid · played safe in 78 of 478 positions where safe paid
Error rate 133.5 (95%: 118.5–148.8) · record 0–0–17 · late entry
Played the original League 1 field after the league finished (late entry)
17 of 19 matches · GPT-6 LunaDecisions API: outside the requested scope (Ümit, 12 Nov); not played (opponent's API out of credit) · Mercury Decide: outside the requested scope (Ümit, 12 Nov); not played (opponent no longer served on OpenRouter)
$0.174 per 1,000 decisions$0.174 per 1M decisions (estimate · DGX Spark) · 1,405 decisions
Cost: Estimate: $0.174 per 1,000 decisions (GPU time, at most). Counted as the wall clock from the first to the last answer, pauses over 10 min left out, × the hourly rate ÷ decisions. 1.2 h on NVIDIA DGX Spark (GB10) × $0.213/h = $0.25; total $0.25 ÷ 1,405 decisions; left out: 2 gaps over 10 min between consecutive answers, 42.1 h in all (each one listed in the data file). NVIDIA DGX Spark (GB10): CHF 4,000 ÷ (3 years × 8,760 h) = CHF 0.152/h purchase + CHF 0.2838/kWh (ewz.natur high rate) × 0.0791 kW (the chip's measured draw, not the whole box) = CHF 0.022/h electricity; CHF 0.175/h ≈ $0.213/h (CHF 1 = $1.2185, ECB 2026-11-10). Other setups' servers may have run on the same machine at the same time; each setup is charged the whole device, so this is an upper bound.
Parameters: 0.44B incl. its projectors, scorer and calibrator; card: 0.4B · dense
Size class by the maker's figure, 0.4B; our checkpoint count 0.44B.
Base model: DeBERTa-v3-large
Tier (same positions) not run yet
Did they improve? (decision models, two arms) notes: waiting (cash approval) · worst: waiting (its render check)
GNUbg weak · x86-64 build: its noise is shifted, so it overplays gammons
Risk judgement 67.1 (95%: 63.8–70.3)
Risks found 66.6% · safe right 67.6%
Took 410 of 616 risks that paid · played safe in 533 of 788 positions where safe paid
Error rate 21.4 (95%: 18.8–24.3) · record 16–0–2
League 1
1,744 decisions
GNUbg weak · x86-64 build: its noise is shifted, so it overplays gammons
Risk judgement 62.3 (95%: 59.5–64.8)
Risks found 62.7% · safe right 61.9%
Took 483 of 770 risks that paid · played safe in 558 of 902 positions where safe paid
Error rate 27.0 (95%: 24.1–29.8) · record 8–0–10
League 2
2,136 decisions
GNUbg weak · x86-64 build: its noise is shifted, so it overplays gammons
Risk judgement 62.1 (95%: 58.2–65.9)
Risks found 58.8% · safe right 65.5%
Took 288 of 490 risks that paid · played safe in 415 of 634 positions where safe paid
Error rate 28.1 (95%: 25.0–31.4) · record 2–2–7
League 3
1,479 decisions
Safest · always plays safe
Risk judgement 50.0 (95%: 50.0–50.0)
Risks found 0.0% · safe right 100.0%
Took 0 of 785 risks that paid · played safe in 749 of 749 positions where safe paid
Error rate 51.6 (95%: 47.4–56.2) · record 4–2–12
League 1
2,058 decisions
Safest (computed)
Risk judgement 50.0 (95%: 50.0–50.0)
Risks found 0.0% · safe right 100.0%
Took 0 of 13,140 risks that paid · played safe in 16,136 of 16,136 positions where safe paid
League 2
Safest (computed)
Risk judgement 50.0 (95%: 50.0–50.0)
Risks found 0.0% · safe right 100.0%
Took 0 of 5,153 risks that paid · played safe in 6,771 of 6,771 positions where safe paid
League 3
Random · a random legal play
Risk judgement 24.9 (95%: 22.3–27.4)
Risks found 24.8% · safe right 25.0%
Took 112 of 452 risks that paid · played safe in 121 of 484 positions where safe paid
Error rate 121.1 (95%: 113.3–128.5) · record 0–0–18
League 1
1,337 decisions
Random (computed)
Risk judgement 27.0 (95%: 26.7–27.2)
Risks found 25.1% · safe right 28.8%
Took 3,300.3 of 13,140 risks that paid · played safe in 4,655.0 of 16,136 positions where safe paid
League 2
Random (computed)
Risk judgement 27.6 (95%: 27.1–28.0)
Risks found 25.1% · safe right 30.1%
Took 1,293.3 of 5,153 risks that paid · played safe in 2,036.5 of 6,771 positions where safe paid
League 3
How each cost is counted
Learning: did they improve?
The leaderboard's Learning tab shows, for every model, its verdict where one is published, else its state in the learning lanes: running, waiting (and why), not tested (and the rule), or not in the learning plan.
How a model is judged. It answers the 200-position risk test 3 times with no memory (before = the mean of those empty runs), then plays 5 series of 10 games against GNUbg weak, writing its own lessons after each game, and takes the test again after game 10 of each series (after = the mean of the 5). Improved? is Yes when risks found rises by more than the improvement threshold (the spread, max − min, of its own 3 empty runs, at least 5 points) and right safety falls by no more than 5 points. This is an operational threshold, not a statistical test. Yes or No only once every run is complete.
Same positions
Preview. The stored answers of the "Did they improve?" test without lessons (E1): 200 positions every model below answered; Muse Ember's answers come from its own run of the same test (12 Nov 2026, its league route and settings). The prompt and setting are the league row's (checked request by request against the league prompts). Engine's best play: the play loses under 0.001 against GNU Backgammon's best; an invalid answer counts as wrong. Tiers: an exact McNemar test on every pair, Holm-adjusted at 0.05; tier 1 is the model with the most best plays and every model not significantly different from it, then the same for the models left. Rank is the league rank.
| Tier | Model | Engine's best play, of 200 | Invalid (counted wrong) | League rank |
|---|---|---|---|---|
| 1 | Claude Fable 5.1high | 106 | 0 | 3 |
| 1 | Claude Opus 5.5high | 106 | 0 | 5 |
| 1 | Claude Sonnet 5.5high | 103 | 0 | 8 |
| 1 | Gemini 4 Argonhigh | 101 | 45 | 2 |
| 1 | DeepSeek-V4.1-Flashlow · API + NVIDIA RTX PRO 6000 Blackwell · first release | 100 | 1 | 6 |
| 1 | Gemini 3.8 Flashhigh | 97 | 0 | 9 |
| 1 | Grok 4.7high | 97 | 0 | 7 |
| 1 | Gemma 4 31Bon · NVIDIA RTX PRO 6000 Blackwell + NVIDIA DGX Spark | 92 | 0 | 13 |
| 1 | Muse Embermax | 88 | 4 | 10 |
| 1 | Kimi K3.1 Prooff | 85 | 0 | 11 |
| 1 | GLM-5.3low | 83 | 0 | 18 |
| 2 | Qwen3.8-27Blow · NVIDIA RTX PRO 6000 Blackwell + NVIDIA DGX Spark | 78 | 0 | 17 |
| 2 | Drex Max v1.1 | 67 | 0 | 25 |
| 2 | Qwen3.8 Flashoff | 66 | 0 | 23 |
| 2 | SubQ Snap 1.1 | 60 | 0 | 34 |
Not asked yet: 26 ranked models (GPT-6 Astrahigh, GPT-6.1 Solhigh, Gemini Decision 1, d1-ultra, Mammoth-1, Drex MaxNVIDIA RTX PRO 6000 Blackwell, KnowLine-31B-Gen1.5NVIDIA DGX Spark (GB10), REAX 1.3, GLiDEAPI, Jev 1.13, Jev 1.14, GLiDEv1.2 · NVIDIA RTX PRO 6000 Blackwell, Drex 2.0, Perplexity Decider 27B v1.2NVIDIA RTX PRO 6000 Blackwell, celeris-1-decision, Elephant-1, Clef, Cygnet, Perplexity Decider 27B v1.1NVIDIA RTX PRO 6000 Blackwell + NVIDIA DGX Spark, SubQ Snap Preview, GPT-6 LunaDecisions API, Winnow-12B, Mercury Decide, LFM2.5-24B-A2Bon · NVIDIA RTX PRO 6000 Blackwell + NVIDIA DGX Spark, Perplexity Decider Flash v1.2, Open-Jev-27B-v1.1NVIDIA RTX PRO 6000 Blackwell). Asking them, one position per request: about $0.4 at list price on hosted APIs ($0.34 for those available now), 19.0 hours one after another, of which 17.7 hours on our GPUs. Not available now: GPT-6 Astrahigh (ChatGPT subscription quota until 13 Nov), GPT-6.1 Solhigh (ChatGPT subscription quota until 13 Nov), GPT-6 LunaDecisions API (no OpenAI API credit).
Models are too cautious.
56 of the 57 ranked models found a worthwhile risk (a risky play at least 0.001 better than the best safe play) in a smaller share of the risk-pays positions than the share of safety-pays positions they played safe: risks found runs from 18.7% to 53.3%, safe right from 16.3% to 97.6%. GNUbg weak, a weak setting of the engine (grey square), is close to even: 67.6% safe right, 66.6% risks found. Above the diagonal, a model succeeds more often when safety pays than when risk pays; the chart compares these two success rates, not how often a model plays risky at all.
Every model's two values
Too safe
Each model's row of the table: the share of its right-safety calls and of the risks it found, as in the table
right safety: played safe when safe was right risks found: took the risk when it paid GNUbg weak, a program: the grey reference pair Bars in the maker's colour, the same rows as the table: OpenAIGoogleAnthropicxAIDeepSeekMoonshotLiquid AIBase LabsAlibabaInceptionNace.AICloudflareZ.aiFastinoPerplexitySubquadraticCelerisEldanRingREAXTypeSafeOmniJevZefan CaiBlockbrain LabsPelaAISthānika AITurion.AIApertix AIStartLuxMetaKnowledgator
OpenAIGoogleAnthropicxAIDeepSeekMoonshotLiquid AIBase LabsAlibabaInceptionNace.AICloudflareZ.aiFastinoPerplexitySubquadraticCelerisEldanRingREAXTypeSafeOmniJevZefan CaiBlockbrain LabsPelaAISthānika AITurion.AIApertix AIStartLuxMetaKnowledgator GNUbg weak (program, reference) Dashed diagonal: as often right on both
Not paired: models met different positions in different leagues. How risks found and safe right are counted
Risk judgement by release date
A release month is documented for 24 of the 57 ranked models; only those are shown, each at the month of its maker's own dated statement. Makers with models in different months, earliest first: Google 64.5, 66.9, 74.1; Fastino 60.4, 58.8. That is not a consistent increase across the makers shown.
OpenAIGoogleAnthropicxAIDeepSeekMoonshotLiquid AIAlibabaCloudflareZ.aiFastinoPerplexityCelerisTypeSafe
Models without a documented release month are left out. How release months are dated
With the numbers on screen, every model asked played safer
Asked which of two plays is better on the same rollout-confirmed positions, all 8 models chose the safe play more often when the prompt showed each play's computed numbers than from the board alone: the bias (missed minus needless) moves from -22 pp to +92 pp for Jev 1.14 and from +46 pp to +56 pp for Claude Opus 5.5high. From the board alone, 4 of them (celeris-1-decision, Jev 1.14, d1-ultra, Kimi K3.1 Prooff) took more needless risks than they missed.
with numbers (the league prompt, each play's computed consequences) board only (notation, no computed number) Bias: missed minus needless, Q1 of Clear risk Part 2
Preliminary: two plays shown, not league play. Clear risk (preliminary)
What thinking adds
9 models played two or more reasoning settings in the same league. At the highest setting, 9 of the 9 had a lower error rate than at the lowest, and 7 of the 9 a higher risk judgement. GPT-6 Astra, low to high: risk judgement 75.8, 74.7, 74.4; error rate 11.8, 11.1, 8.8.
One row per model and league; hollow dots: its lower settings, filled dot: its highest setting. OpenAIGoogleAnthropicDeepSeekLiquid AI
Not paired: each setting played its own games; these are observed differences. Every setting, league by league
A new starting position
Each model was asked Nackgammon positions and standard positions matched to them. Compared group against group (one group's drop minus another's; a group is the setups from one original league: League 1, 2, 3), every 99% interval includes 0, so the test does not show the groups' drops to differ. Random play's own drop is −4.6 PR on the main 200 pairs: the Nackgammon positions were slightly easier for random play. Outside the groups, the late entry Elephant-1 dropped (+8.66 PR, 97.5% interval +0.42 to +16.02). Unclear means the test can’t tell, not that the scores are equal.
OpenAIGoogleAnthropicxAIDeepSeekLiquid AIAlibabaInceptionFastinoPerplexitySubquadraticCelerisEldanRingTypeSafeZefan CaiBlockbrain Labs GNUbg weak, Random (programs) Above the dashed diagonal: higher error on Nackgammon.
Paired positions, not league play; a drop mixes the new start with how hard the positions are. The Nackgammon test
Does the model learn from its games?
Status: Done. No arm reached the pre-registered signal threshold (plan section 8).
no memoryfull recordsown lessonsbudget (empty: no game fit)
Swipe for more columns →
| Arm | Series | Before game 1 | After game 5 | After game 10 |
|---|---|---|---|---|
| no memory | 10 | 25.0 | T0 only | T0 only |
| full records | 10 | 25.0 | 28.8 | 28.3 |
| own lessons | 10 | 25.0 | 34.6 | 33.3 |
| budget (empty: no game fit) | 10 | 25.0 | 28.7 | 27.8 |
no memory is tested before game 1 only (the shared run): its line is drawn flat and dashed at that value.
One model, a small pilot; the plan, every number and the lessons are on its page. Learning from experience
How the scores work
- Models play full games of backgammon. GNU Backgammon scores every move.
- Risk judgement: did the model find a worthwhile risk when risk paid, and play safe when safe was right? 50 = always plays safe, 100 = every call right.
- Error rate: how much a move gives away, judged by the engine (lower is better).
- Everything is public: every position, every legal play, the engine's value for each.
- Leagues played different positions, so close scores across leagues are not a clear ranking.