Model comparison
Mistral vs Mistral Medium
Mistral Medium is the stronger model overall, scoring 36.3 to 29.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
Mistral AISummary
- They share 17 benchmarks with published results for both. Mistral scores higher in 0 categories and Mistral Medium in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Medium leads 60.0 to 37.0.
- Mistral Medium has downloadable open weights; the other is API-only.
Side by side
| Mistral | Mistral Medium | |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 29.9 | 36.3 |
| Released | — | 2023-12-11 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 262K |
| Input $ / M tokens | — | $1.50 |
| Output $ / M tokens | — | $7.50 |
| Results tracked | 22 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Mistral: 33.8 (#250), Mistral Medium: 34.2 (#243)
| Benchmark | Mistral | Mistral Medium |
|---|---|---|
| LMArena Coding | 1162 | 1434 |
| FrontierCode | — | 8% |
| SciCode | — | 40.2% |
| WeirdML | — | 43.7% |
| ALE-Bench | — | 763.98 |
Agentic & Tool Use Not comparable
Mistral: —, Mistral Medium: 28.3 (#90)
| Benchmark | Mistral | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.7% |
Reasoning Mistral Medium leads
Mistral: 22.2 (#200), Mistral Medium: 24.0 (#167)
| Benchmark | Mistral | Mistral Medium |
|---|---|---|
| LMArena Hard Prompts | 1149 | 1426 |
| Kagi LLM Benchmark | — | 50% |
| CritPt | — | 0% |
| DTBench | — | 75.5% |
| LMCA | — | 26.1% |
| Surface Evolver Bench | — | 26.9% |
Math Mistral Medium leads
Mistral: 22.3 (#278), Mistral Medium: 28.1 (#245)
| Benchmark | Mistral | Mistral Medium |
|---|---|---|
| LMArena Math | 1180 | 1408 |
| OTIS Mock AIME 2024-2025 | — | 32.2% |
| ProofBench | — | 9% |
| Omni-MATH | 7.2% | — |
| MATH Level 5 | — | 81.6% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge Mistral Medium leads
Mistral: 16.6 (#288), Mistral Medium: 25.0 (#265)
| Benchmark | Mistral | Mistral Medium |
|---|---|---|
| LMArena Expert | 1125 | 1408 |
| GPQA Diamond | — | 59.5% |
| Humanity's Last Exam | — | 4.5% |
| MMLU-Pro | 27.7% | — |
| Vectara Hallucination Rate | — | 22.7% |
| GPQA (HELM) | 30.3% | — |
Multimodal Not comparable
Mistral: —, Mistral Medium: 35.3 (#88)
| Benchmark | Mistral | Mistral Medium |
|---|---|---|
| LMArena Vision | — | 1172 |
Multilingual Mistral Medium leads
Mistral: 32.8 (#254), Mistral Medium: 52.1 (#91)
| Benchmark | Mistral | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1129 | 1408 |
| LMArena Chinese | 1109 | 1447 |
| LMArena French | 1180 | 1459 |
| LMArena German | 1155 | 1432 |
| LMArena Japanese | 1013 | 1378 |
| LMArena Korean | 1032 | 1380 |
| LMArena Russian | 1168 | 1411 |
| LMArena Spanish | 1143 | 1433 |
Instruction Following Mistral Medium leads
Mistral: 52.6 (#288), Mistral Medium: 73.7 (#116)
| Benchmark | Mistral | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1152 | 1398 |
| IFEval | 56.8% | — |
Long Context Mistral Medium leads
Mistral: 35.0 (#245), Mistral Medium: 42.9 (#114)
| Benchmark | Mistral | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1153 | 1406 |
Writing & Preference Mistral Medium leads
Mistral: 37.0 (#260), Mistral Medium: 60.0 (#103)
| Benchmark | Mistral | Mistral Medium |
|---|---|---|
| LMArena Text | 1165 | 1424 |
| LMArena Creative Writing | 1158 | 1391 |
| LMArena Multi-Turn | 1147 | 1418 |
| Short-Story Creative Writing | — | 77.3% |
| WildBench | 66% | — |
Frequently asked questions
Is Mistral better than Mistral Medium?
Mistral Medium is the stronger model overall, scoring 36.3 to 29.9 on the Noometry Index.
Is Mistral or Mistral Medium better for coding?
They score almost the same on coding (33.8 vs 34.2); test both on your own repository before choosing.
How many benchmarks do Mistral and Mistral Medium share?
17 benchmarks have published results for both models. Mistral has 22 scored results on Noometry and Mistral Medium has 36.