Overall score
36.9
Rank #87 · B confidence
Mistral AI · stable
Mistral AI's documented open-weight general-purpose multimodal model.
Overall score
36.9
Rank #87 · B confidence
Capability
30.0
19 eligible benchmark families
Coverage
67%
Confidence B
Benchmarks scored
19
20 raw result rows
Model specification
Identity, configuration and price are preserved as dated source records.
Category profile
A category remains Not evaluated until an eligible source-qualified result is attached.
Benchmark scores
Best published score per benchmark. Open any row for the full per-benchmark leaderboard.
| Benchmark | Category | Score | Date |
|---|---|---|---|
| GPQA DiamondRanking weighted | reasoning | 67.98% | 2026-07-15 |
| MMMU-ProRanking weighted | multimodal | 55.7% | 2026-07-15 |
| Arena-Hard-Auto | instruction following | 55.1% | 2026-07-15 |
| LiveCodeBenchRanking weighted | coding | 46.46% | 2026-07-15 |
| IFBench | instruction following | 36.2% | 2026-07-15 |
| IFEval | instruction following | 36.2% | 2026-07-15 |
| SciCodeRanking weighted | coding | 36.2% | 2026-07-15 |
| AA Long Context ReasoningRanking weighted | research | 34.6667% | 2026-07-15 |
| GAIARanking weighted | agents | 30.8% | 2026-07-15 |
| τ-benchRanking weighted | agents | 24.6% | 2026-07-15 |
| τ²-Bench TelecomRanking weighted | agents | 24.5614% | 2026-07-15 |
| Terminal-Bench HardRanking weighted | agents | 15.9091% | 2026-07-15 |
| Long-Horizon-Terminal-BenchRanking weighted | agents | 15.9% | 2026-07-15 |
| Terminal-BenchRanking weighted | agents | 11.99% | 2026-07-15 |
| GDPval-AA v2Ranking weighted | agents | 6.6255% | 2026-07-15 |
| τ³-BankingRanking weighted | agents | 5.7732% | 2026-07-15 |
| Humanity's Last ExamRanking weighted | reasoning | 4.08% | 2026-07-15 |
| AA-OmniscienceRanking weighted | research | -39.4333 index | 2026-07-15 |
| CritPtRanking weighted | reasoning | 0% | 2026-07-15 |
Showing the best of 20 raw result rows across 19 benchmark families.
Price and efficiency
Operational values are shown only when the source publishes a comparable measurement or a valid derivation.
Verification summary
News and X posts are structurally excluded from this model's evidence graph.
Missing publication dimensions: value. The last source check for this exact model was 2026-07-16.
Related models
Exact variants remain separate even when they share a provider or family.