mistral-7b-instruct-v0.2
33±0
33interval34
aiqbench · LLM benchmarks
33±0
33interval34
27±0
26interval28
23±0
23interval24
One grid, every column. Pick axes in the Axes panel — one axis ranks like a single board, several blend into a weighted composite, all of them read as the index. Rank is assigned before any filter and never renumbers.
| Model | Org | Interval | Swing | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | Add to compare | |||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 965 | mistral-7b-instruct-v0.2 | mistral | Dec 2023 | — | 33.3 8.2Ranked 33.3 = (2 × 8.2 + 3 × 50) ÷ 5. 8.2 is the mean percentile over the 2 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | 33–34 | 3 | 2/22low | #368–965 | 10 | — | — | — | — | — | — | — | — | — | — | — | — | — | 7 | — | — | — | — | — | — | — | ||
| 1021 | Mistral-7B-Instruct-v0.3 | Mistral AI | — | — | 26.8 3.7Ranked 26.8 = (3 × 3.7 + 3 × 50) ÷ 6. 3.7 is the mean percentile over the 3 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | 26–28 | 6 | 3/22 | #482–1021 | — | — | — | — | — | — | — | 2 | 2 | — | — | — | — | — | 7 | — | — | — | — | — | — | — | ||
| 1032 | mistral-7b-instruct | mistral | Sep 2023 | — | 23.4 3.5Ranked 23.4 = (4 × 3.5 + 3 × 50) ÷ 7. 3.5 is the mean percentile over the 4 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | 23–24 | 2 | 4/22 | #394–1032 | 5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 3 | 4 | 3 | — |
Blend is coverage-shrunk; the raw composite is shown greyed beside it · A low badge means fewer than 3 boards scored this model