Model comparison
MiniMax-M2.5 vs Mistral
MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 29.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
MiniMax
Mistral AISummary
- They share 17 benchmarks with published results for both. MiniMax-M2.5 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-M2.5 leads 39.2 to 16.6.
- MiniMax-M2.5 has downloadable open weights; the other is API-only.
Side by side
| MiniMax-M2.5 | Mistral | |
|---|---|---|
| Provider | MiniMax | Mistral AI |
| Noometry Index | 38.3 | 29.9 |
| Released | 2026-02-12 | — |
| Weights | Open | Proprietary |
| Context window | 205K | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $1.20 | — |
| Results tracked | 33 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.5 leads
MiniMax-M2.5: 48.1 (#58), Mistral: 33.8 (#250)
| Benchmark | MiniMax-M2.5 | Mistral |
|---|---|---|
| LMArena Coding | 1381 | 1162 |
| SWE-bench Verified (bash only) | 75.8% | — |
| LMArena WebDev | 1387 | — |
| SWE-bench Multilingual | 68.3% | — |
| ALE-Bench | 618.17 | — |
Agentic & Tool Use Not comparable
MiniMax-M2.5: 30.4 (#77), Mistral: —
| Benchmark | MiniMax-M2.5 | Mistral |
|---|---|---|
| Terminal-Bench | 42.7% | — |
| Vending-Bench 2 | -23.16 | — |
Reasoning Mistral leads
MiniMax-M2.5: 17.5 (#292), Mistral: 22.2 (#200)
| Benchmark | MiniMax-M2.5 | Mistral |
|---|---|---|
| LMArena Hard Prompts | 1372 | 1149 |
| ARC-AGI-2 | 4.9% | — |
| Kagi LLM Benchmark | 55.2% | — |
| NYT Connections (extended) | 16.8% | — |
| ARC-AGI-1 | 63.7% | — |
| Epoch Capabilities Index | 146.68 | — |
Math MiniMax-M2.5 leads
MiniMax-M2.5: 26.9 (#253), Mistral: 22.3 (#278)
| Benchmark | MiniMax-M2.5 | Mistral |
|---|---|---|
| LMArena Math | 1378 | 1180 |
| ProofBench | 4% | — |
| Omni-MATH | — | 7.2% |
Knowledge MiniMax-M2.5 leads
MiniMax-M2.5: 39.2 (#135), Mistral: 16.6 (#288)
| Benchmark | MiniMax-M2.5 | Mistral |
|---|---|---|
| LMArena Expert | 1379 | 1125 |
| MMLU-Pro | — | 27.7% |
| Vectara Hallucination Rate | 9.1% | — |
| GPQA (HELM) | — | 30.3% |
Multilingual MiniMax-M2.5 leads
MiniMax-M2.5: 47.1 (#152), Mistral: 32.8 (#254)
| Benchmark | MiniMax-M2.5 | Mistral |
|---|---|---|
| LMArena Non-English | 1338 | 1129 |
| LMArena Chinese | 1393 | 1109 |
| LMArena French | 1362 | 1180 |
| LMArena German | 1362 | 1155 |
| LMArena Japanese | 1171 | 1013 |
| LMArena Korean | 1232 | 1032 |
| LMArena Russian | 1358 | 1168 |
| LMArena Spanish | 1354 | 1143 |
Instruction Following MiniMax-M2.5 leads
MiniMax-M2.5: 71.5 (#148), Mistral: 52.6 (#288)
| Benchmark | MiniMax-M2.5 | Mistral |
|---|---|---|
| LMArena Instruction Following | 1353 | 1152 |
| IFEval | — | 56.8% |
Long Context MiniMax-M2.5 leads
MiniMax-M2.5: 37.5 (#216), Mistral: 35.0 (#245)
| Benchmark | MiniMax-M2.5 | Mistral |
|---|---|---|
| LMArena Longer Query | 1366 | 1153 |
| CL-bench | 11.4% | — |
| CL-bench Life | 6.3% | — |
Writing & Preference MiniMax-M2.5 leads
MiniMax-M2.5: 53.9 (#153), Mistral: 37.0 (#260)
| Benchmark | MiniMax-M2.5 | Mistral |
|---|---|---|
| LMArena Text | 1359 | 1165 |
| LMArena Creative Writing | 1331 | 1158 |
| LMArena Multi-Turn | 1364 | 1147 |
| EQ-Bench Creative Writing | 1361 | — |
| WildBench | — | 66% |
Frequently asked questions
Is MiniMax-M2.5 better than Mistral?
MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 29.9 on the Noometry Index.
Is MiniMax-M2.5 or Mistral better for coding?
MiniMax-M2.5 scores higher on coding benchmarks: 48.1 versus 33.8 in the Noometry coding category.
How many benchmarks do MiniMax-M2.5 and Mistral share?
17 benchmarks have published results for both models. MiniMax-M2.5 has 33 scored results on Noometry and Mistral has 22.