Model comparison
MiniMax-M2 vs Mistral
MiniMax-M2 is the stronger model overall, scoring 37.4 to 29.9 on the Noometry Index.
Last verified . 15 shared benchmarks.
MiniMax
Mistral AISummary
- They share 15 benchmarks with published results for both. MiniMax-M2 scores higher in 7 categories and Mistral in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M2 leads 37.0 to 16.6.
- MiniMax-M2 has downloadable open weights; the other is API-only.
Side by side
| MiniMax-M2 | Mistral | |
|---|---|---|
| Provider | MiniMax | Mistral AI |
| Noometry Index | 37.4 | 29.9 |
| Released | 2025-10-27 | — |
| Weights | Open | Proprietary |
| Context window | 205K | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $1.20 | — |
| Results tracked | 21 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2 leads
MiniMax-M2: 39.3 (#159), Mistral: 33.8 (#250)
| Benchmark | MiniMax-M2 | Mistral |
|---|---|---|
| LMArena Coding | 1370 | 1162 |
| SWE-bench Verified (bash only) | 61% | — |
| LMArena WebDev | 1297 | — |
Agentic & Tool Use Not comparable
MiniMax-M2: 25.1 (#109), Mistral: —
| Benchmark | MiniMax-M2 | Mistral |
|---|---|---|
| Terminal-Bench | 30% | — |
| Vending-Bench 2 | 160.6 | — |
Reasoning Mistral leads
MiniMax-M2: 19.4 (#258), Mistral: 22.2 (#200)
| Benchmark | MiniMax-M2 | Mistral |
|---|---|---|
| LMArena Hard Prompts | 1357 | 1149 |
| Kagi LLM Benchmark | 57.8% | — |
| NYT Connections (extended) | 14.8% | — |
Math MiniMax-M2 leads
MiniMax-M2: 37.3 (#160), Mistral: 22.3 (#278)
| Benchmark | MiniMax-M2 | Mistral |
|---|---|---|
| LMArena Math | 1352 | 1180 |
| Omni-MATH | — | 7.2% |
Knowledge MiniMax-M2 leads
MiniMax-M2: 37.0 (#163), Mistral: 16.6 (#288)
| Benchmark | MiniMax-M2 | Mistral |
|---|---|---|
| LMArena Expert | 1337 | 1125 |
| MMLU-Pro | — | 27.7% |
| GPQA (HELM) | — | 30.3% |
Multilingual MiniMax-M2 leads
MiniMax-M2: 45.3 (#171), Mistral: 32.8 (#254)
| Benchmark | MiniMax-M2 | Mistral |
|---|---|---|
| LMArena Non-English | 1313 | 1129 |
| LMArena Chinese | 1366 | 1109 |
| LMArena French | 1335 | 1180 |
| LMArena German | 1355 | 1155 |
| LMArena Russian | 1331 | 1168 |
| LMArena Spanish | 1326 | 1143 |
| LMArena Japanese | — | 1013 |
| LMArena Korean | — | 1032 |
Instruction Following MiniMax-M2 leads
MiniMax-M2: 70.2 (#166), Mistral: 52.6 (#288)
| Benchmark | MiniMax-M2 | Mistral |
|---|---|---|
| LMArena Instruction Following | 1328 | 1152 |
| IFEval | — | 56.8% |
Long Context MiniMax-M2 leads
MiniMax-M2: 40.5 (#153), Mistral: 35.0 (#245)
| Benchmark | MiniMax-M2 | Mistral |
|---|---|---|
| LMArena Longer Query | 1331 | 1153 |
Writing & Preference MiniMax-M2 leads
MiniMax-M2: 53.0 (#162), Mistral: 37.0 (#260)
| Benchmark | MiniMax-M2 | Mistral |
|---|---|---|
| LMArena Text | 1340 | 1165 |
| LMArena Creative Writing | 1286 | 1158 |
| LMArena Multi-Turn | 1361 | 1147 |
| WildBench | — | 66% |
Frequently asked questions
Is MiniMax-M2 better than Mistral?
MiniMax-M2 is the stronger model overall, scoring 37.4 to 29.9 on the Noometry Index.
Is MiniMax-M2 or Mistral better for coding?
MiniMax-M2 scores higher on coding benchmarks: 39.3 versus 33.8 in the Noometry coding category.
How many benchmarks do MiniMax-M2 and Mistral share?
15 benchmarks have published results for both models. MiniMax-M2 has 21 scored results on Noometry and Mistral has 22.