chat model, answer-letter probabilities · League 2

DeepSeek-V4.1-Flashlow · API · 1017

FinishedPublished

Results f24d1f41, updated 16 November 2026, 21:24 UTC; scored by GNU Backgammon 1.08, 2-ply.

How we called it

Model ID
deepseek/deepseek-v4.1-flash-1017
Provider or endpoint
DeepSeek (first party) via OpenRouter, provider pinned, no fallbacks; quantization not published
Date run
24–28 Oct 2026
Price
$0.15 / $0.6 per million tokens in / out; API price; price date 2026-10-24
Model type
chat model, answer-letter probabilities
Weights
open
Runs on
API
Reasoning setting
thinking on, reasoning effort low
Confidence source
letter probability
Rules text
long
Option groups
up to 26 options per request (letters A-Z); more legal plays are split into equal groups, a winner per group, then among the winners; in this data 258 decisions were split into groups of 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26
Sampling settings
temperature 1.0
Notes
The 17 Oct 2026 snapshot of DeepSeek-V4.1-Flash, served by DeepSeek itself through OpenRouter (provider pinned, fallbacks off) for every decision; never on our GPUs. Late entry to League 2 on 24 Oct 2026; its missing pairings were played on 27–28 Oct 2026. No fixed answer format (DeepSeek's endpoint takes no JSON schema): the letter is read from the free-text answer with its probabilities. DeepSeek may train on paid prompts; allowed by Can, 24 Oct 2026.
Earlier name
DeepSeek-V4.1-Flash1017 (on) (renamed on 28 Oct 2026 to the reasoning effort its requests sent)

Results in League 2

Error rate (PR)
17.115.1 to 19.2
Decisions
2,234 (2,222 scored, 12 invalid)
Engine's best play
61.8%
Blunder rate
13.4%
P95 equity loss
0.199
Mean loss, worst 5%
0.330
Median / P90 s per decision
22.3 / 107.6
$ per 1,000 decisions
4.869API price
Risk judgement, margin 0.001
68.5 (95% interval 66.4 to 70.6); risks found 42.5% (321 / 755), right safety 94.5% (872 / 923)
Risk judgement, margin 0.02
68.9 (95% interval 66.5 to 71.3); risks found 44.8% (293 / 654), right safety 93.0% (952 / 1,024)
No trade-off
544 (left out of every risk metric)

JSON

Risk call card

68.5risk judgement, margin 0.001

right risks321
wrong risks41
needless risks51
missed risks393
right safety872

Hit risk only: being hit. Gammon risk and priming are not in it.

Close choices

A decision is a close choice when the second most likely play has at least half the probability of the first (internally: split).

Probabilities over plays, not sampled reasoning. Method

League 2: complete letter-readout records are mostly few-option positions, a selected subset.

Decisions
2,234
Eligible (full probability distribution)
180
Left out, by reason
invalid answers 12; asked in groups of options 204; incomplete distribution (an option without its own probability) 1,311; not audited 527
Close choices
0.0% (0 / 180), under 200 decisions
Ties in the top two
0 decisions (0 at a positive probability, 0 at 0; the two most likely plays tied: 0, the second tied with the third: 0); 0 of them close choices. Ties are broken by the order the plays were shown, never by the engine.
Between a safe play and a riskier one
N/A (0 / 0) of the close choices; 0.0% (0 / 180), under 200 decisions of all eligible decisions
Probabilities of the two most likely plays, mean with median
DecisionsNumberp1 (most likely play)p2 (second)p1 + p2
Close choices0N/AN/AN/A
Other decisions1801.000median 1.0000.000median 0.0001.000median 1.000
How much probability the two plays hold together: decisions per bin
p1 + p20.0–0.10.1–0.20.2–0.30.3–0.40.4–0.50.5–0.60.6–0.70.7–0.80.8–0.90.9–1.0
Close choices0000000000
Other decisions000000000180
What differs between the two most likely plays (several can differ; none is picked as the cause)
DecisionsNumberHitting rollsNewly made pointsPip countsLongest primeNone / 1 / 2 / 3 / 4 differ
Close choices0N/A0 / 0N/A0 / 0N/A0 / 0N/A0 / 00 / 0 / 0 / 0 / 0
Other decisions18041.1%74 / 180, under 200 decisions16.1%29 / 180, under 200 decisions16.7%30 / 180, under 200 decisions25.6%46 / 180, under 200 decisions54 / 81 / 37 / 8 / 0
Engine values (GNUbg 2-ply, equity), mean with median
DecisionsNumberGap between the two plays' valuesMost likely play: behind the engine's bestSecond most likely play: behind the engine's best
Close choices0N/AN/AN/A
Other decisions1800.118median 0.0510.007median 0.0000.114median 0.040
Close choices between a safe play and a riskier one, by position class
MarginIn Risk pays positionsIn Safety pays positions
margin 0.001N/A0 / 0N/A0 / 0
margin 0.02N/A0 / 0N/A0 / 0
Close choices among eligible decisions, by position class and stake band
MarginRisk paysSafety paysNo trade-offRisk pays, small stakeRisk pays, medium stakeRisk pays, big stake
margin 0.0010.0%0 / 22, under 200 decisions0.0%0 / 58, under 200 decisions0.0%0 / 100, under 200 decisions0.0%0 / 4, under 200 decisions0.0%0 / 9, under 200 decisions0.0%0 / 9, under 200 decisions
margin 0.020.0%0 / 18, under 200 decisions0.0%0 / 62, under 200 decisions0.0%0 / 100, under 200 decisionsN/A0 / 00.0%0 / 9, under 200 decisions0.0%0 / 9, under 200 decisions

At the 0.02 margin a Risk pays position has a stake of at least 0.02, so the small band is empty. A big stake means playing safe costs more by the engine's value, not that the decision was harder.

Missed risks where the risk is worth taking, close choices vs other decisions
MarginClose choices: missed risksOther decisions: missed risks (weighted to the close choices' mix)Difference, close minus otherCrude difference
margin 0.00120 decisionsN/AN/A (0 / 0)70.0%70.0% (14 / 20), under 200 decisionsN/A: no close choices in this groupN/A
margin 0.0217 decisionsN/AN/A (0 / 0)64.7%64.7% (11 / 17), under 200 decisionsN/A: no close choices in this groupN/A

By game phase

PhaseError rate (PR)Decisions
Opening15.7318
Contact21.61,439
Holding gameToo few decisions66
Race4.7238
Bear-offToo few decisions161