Mistral
availableShows if the model has enough results for an index.Mistral Medium 3
Mistral Medium 3 is a non-reasoning model from Mistral. 13 benchmarks count toward its score, in 6 categories.
IndexOverall score. 50 is the middle.30.5 ±7.0
CoverageShare of the index weight with results.75%
SpeedOutput tokens per second.35/s
Input / 1MUS dollars per 1M input tokens.$0.4
Output / 1MUS dollars per 1M output tokens.$2
ContextMaximum tokens in one request.131K
EloLMArena rating and rank.N/A
50 is the middle of the board. The range shows the doubt in the index.
CapabilitiesScore per category. 50 is the middle.
50 is the middleResults
13 counted| BenchmarkThe test name. | CategoryThe capability that the test measures. | ResultThe score from the publisher. | IndexThis result on the index scale. | RunThe settings of the run. | DateDate of the result. | Published byThe source of the result. |
|---|---|---|---|---|---|---|
| MATH level 5 | Math | 81.6% | 38.8 | — | — | Epoch AI |
| GPQA diamond | Knowledge | 59.5% | 33.2 | — | — | Epoch AI |
| Artificial Analysis GPQA Diamond | Knowledge | 57.8% | 27.8 | — | — | Artificial Analysis |
| Artificial Analysis MMMU-Pro | Multimodal | 53.0% | 31.9 | — | — | Artificial Analysis |
| Artificial Analysis IFBench | Instruction | 39.3% | 29.0 | — | — | Artificial Analysis |
| OTIS Mock AIME 2024-2025 | Math | 32.2% | 29.6 | — | — | Epoch AI |
| Artificial Analysis Long Context Reasoning | Reasoning | 31.3% | 29.9 | — | — | Artificial Analysis |
| τ²-Bench Tool-Agent-User Evaluation | Agentic | 24.3% | 16.3 | — | — | Victor Barres et al. |
| Artificial Analysis Omniscience Accuracy | Knowledge | 18.3% | 36.5 | — | — | Artificial Analysis |
| Artificial Analysis Intelligence Index | Knowledge | 9.1% | 33.7 | — | — | Artificial Analysis |
| Artificial Analysis Humanity's Last Exam | Knowledge | 4.1% | 29.0 | — | — | Artificial Analysis |
| FrontierMath-2025-02-28-Private | Math | 0.3% | 31.0 | — | — | Epoch AI |
| Critical Physics Tasks | Reasoning | 0.0% | 38.4 | — | — | Artificial Analysis |
13 benchmarks count, from 13 of 13 results. A grey row does not count. Too few models took that benchmark.