Model comparison
Mistral vs Mistral Small
Mistral Small is the stronger model overall, scoring 33.1 to 29.4 on the Noometry Index.
Last verified . 17 shared benchmarks.
Mistral AISummary
- They share 17 benchmarks with published results for both. Mistral scores higher in 2 categories and Mistral Small in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Small leads 52.6 to 37.2.
- Mistral Small has downloadable open weights; the other is API-only.
Side by side
| Mistral | Mistral Small | |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 29.4 | 33.1 |
| Released | — | 2024-02-26 |
| Weights | Proprietary | Open |
| Context window | — | 256K |
| Max output | — | 256K |
| Input $ / M tokens | — | $0.15 |
| Output $ / M tokens | — | $0.60 |
| Results tracked | 22 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Mistral: 33.2 (#249), Mistral Small: 33.5 (#242)
| Benchmark | Mistral | Mistral Small |
|---|---|---|
| LMArena Coding | 1162 | 1363 |
| SciCode | — | 26.5% |
| BigCodeBench Instruct | — | 36.1% |
| LiveBench Coding | — | 36.2% |
| BigCodeBench Complete | — | 46.6% |
| ALE-Bench | — | 497.62 |
Agentic & Tool Use Not comparable
Mistral: —, Mistral Small: 27.9 (#87)
| Benchmark | Mistral | Mistral Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.1% |
Reasoning Mistral leads
Mistral: 21.3 (#199), Mistral Small: 19.3 (#238)
| Benchmark | Mistral | Mistral Small |
|---|---|---|
| LMArena Hard Prompts | 1149 | 1336 |
| Kagi LLM Benchmark | — | 37.8% |
| CritPt | — | 0% |
| LiveBench Reasoning | — | 44.8% |
| DTBench | — | 70.9% |
| LiveBench Data Analysis | — | 53.7% |
| LMCA | — | 20.6% |
| LiveBench | — | 44% |
Math Mistral leads
Mistral: 20.5 (#275), Mistral Small: 15.4 (#287)
| Benchmark | Mistral | Mistral Small |
|---|---|---|
| LMArena Math | 1180 | 1341 |
| OTIS Mock AIME 2024-2025 | — | 5.8% |
| Omni-MATH | 7.2% | — |
| LiveBench Math | — | 39.9% |
| MATH Level 5 | — | 46.8% |
Knowledge Mistral Small leads
Mistral: 16.3 (#283), Mistral Small: 30.9 (#214)
| Benchmark | Mistral | Mistral Small |
|---|---|---|
| LMArena Expert | 1125 | 1293 |
| GPQA Diamond | — | 47.5% |
| MMLU-Pro | 27.7% | — |
| Vectara Hallucination Rate | — | 5.1% |
| GPQA (HELM) | 30.3% | — |
| MMLU | — | 68.7% |
Multimodal Not comparable
Mistral: —, Mistral Small: 32.9 (#91)
| Benchmark | Mistral | Mistral Small |
|---|---|---|
| LMArena Vision | — | 1142 |
Multilingual Mistral Small leads
Mistral: 33.0 (#249), Mistral Small: 45.7 (#164)
| Benchmark | Mistral | Mistral Small |
|---|---|---|
| LMArena Non-English | 1129 | 1315 |
| LMArena Chinese | 1109 | 1342 |
| LMArena French | 1179 | 1337 |
| LMArena German | 1155 | 1341 |
| LMArena Japanese | 1012 | 1275 |
| LMArena Korean | 1032 | 1260 |
| LMArena Russian | 1168 | 1324 |
| LMArena Spanish | 1143 | 1346 |
Instruction Following Mistral Small leads
Mistral: 52.9 (#283), Mistral Small: 66.6 (#204)
| Benchmark | Mistral | Mistral Small |
|---|---|---|
| LMArena Instruction Following | 1152 | 1310 |
| LiveBench Instruction Following | — | 63.7% |
| IFEval | 56.8% | — |
Long Context Mistral Small leads
Mistral: 35.0 (#240), Mistral Small: 40.4 (#151)
| Benchmark | Mistral | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1154 | 1327 |
Writing & Preference Mistral Small leads
Mistral: 37.2 (#255), Mistral Small: 52.6 (#165)
| Benchmark | Mistral | Mistral Small |
|---|---|---|
| LMArena Text | 1165 | 1338 |
| LMArena Creative Writing | 1158 | 1304 |
| LMArena Multi-Turn | 1147 | 1344 |
| WildBench | 66% | — |
| LiveBench Language | — | 30.5% |
Frequently asked questions
Is Mistral better than Mistral Small?
Mistral Small is the stronger model overall, scoring 33.1 to 29.4 on the Noometry Index.
Is Mistral or Mistral Small better for coding?
They score almost the same on coding (33.2 vs 33.5); test both on your own repository before choosing.
How many benchmarks do Mistral and Mistral Small share?
17 benchmarks have published results for both models. Mistral has 22 scored results on Noometry and Mistral Small has 39.