chat model, answer-letter probabilities · New models: first look (50 smoke positions)
MiMo-V2.6-Flashlow
Smoke test
Results f24d1f41, updated 16 November 2026, 22:20 UTC; scored by GNU Backgammon 1.08, 2-ply.
How we called it
- Model ID
- xiaomi/mimo-v2.6-flash
- Provider or endpoint
- OpenRouter, pinned to Makora (fp8)
- Date run
- 2026-10-21
- Price
- $0.13 / $0.28 per million tokens in / out; API price; price date 2026-10-21
- Model type
- chat model, answer-letter probabilities
- Weights
- open
- Runs on
- API
- Reasoning setting
- reasoning effort low
- Confidence source
- letter probability
- Rules text
- long
- Option groups
- one request (no split)
- Sampling settings
- temperature 1.0
- Notes
- Missing
Smoke test
- Positions answered
- 50 of 50 (0 failed, 0 timed out)
- Invalid answers
- 14
- Error rate (PR)
- 7.7 (95% interval 1.6 to 15.4)
- Median / P90 request s
- 39.5 / 332.7
- $ per 1,000 decisions
- 3.62