Model comparison
Mistral Small 3.1 vs Qwen2.5-Max
Qwen2.5-Max is the stronger model overall, scoring 40.1 to 31.4 on the Noometry Index.
Last verified . 18 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Mistral Small 3.1 scores higher in 0 categories and Qwen2.5-Max in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen2.5-Max leads 34.3 to 13.7.
- Mistral Small 3.1 has downloadable open weights; the other is API-only.
Side by side
| Mistral Small 3.1 | Qwen2.5-Max | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 31.4 | 40.1 |
| Released | 2025-03-17 | 2025-01-25 |
| Weights | Open | Proprietary |
| Context window | 128K | — |
| Max output | 102K | — |
| Input $ / M tokens | $0.35 | — |
| Output $ / M tokens | $0.56 | — |
| Results tracked | 28 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5-Max leads
Mistral Small 3.1: 37.7 (#175), Qwen2.5-Max: 41.2 (#118)
| Benchmark | Mistral Small 3.1 | Qwen2.5-Max |
|---|---|---|
| LMArena Coding | 1309 | 1359 |
| LiveBench Coding | — | 64.4% |
Reasoning Qwen2.5-Max leads
Mistral Small 3.1: 18.9 (#249), Qwen2.5-Max: 24.6 (#144)
| Benchmark | Mistral Small 3.1 | Qwen2.5-Max |
|---|---|---|
| LMArena Hard Prompts | 1278 | 1360 |
| Epoch Capabilities Index | 127.48 | 132.54 |
| Chess Puzzles | 1% | — |
| LiveBench Reasoning | — | 51.4% |
| LiveBench Data Analysis | — | 67.9% |
| LiveBench | — | 62.3% |
Math Qwen2.5-Max leads
Mistral Small 3.1: 13.7 (#295), Qwen2.5-Max: 34.3 (#162)
| Benchmark | Mistral Small 3.1 | Qwen2.5-Max |
|---|---|---|
| LMArena Math | 1261 | 1369 |
| OTIS Mock AIME 2024-2025 | 3.9% | — |
| Omni-MATH | 24.8% | — |
| LiveBench Math | — | 58.4% |
Knowledge Qwen2.5-Max leads
Mistral Small 3.1: 22.6 (#266), Qwen2.5-Max: 34.8 (#181)
| Benchmark | Mistral Small 3.1 | Qwen2.5-Max |
|---|---|---|
| LMArena Expert | 1258 | 1337 |
| GPQA Diamond | 41.9% | — |
| MMLU-Pro | 61% | — |
| Confabulations | — | 21.8% |
| GPQA (HELM) | 39.2% | — |
Multimodal Not comparable
Mistral Small 3.1: 32.6 (#93), Qwen2.5-Max: —
| Benchmark | Mistral Small 3.1 | Qwen2.5-Max |
|---|---|---|
| LMArena Vision | 1136 | — |
Multilingual Qwen2.5-Max leads
Mistral Small 3.1: 41.4 (#204), Qwen2.5-Max: 48.3 (#140)
| Benchmark | Mistral Small 3.1 | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | 1255 | 1352 |
| LMArena Chinese | 1254 | 1382 |
| LMArena French | 1270 | 1396 |
| LMArena German | 1266 | 1350 |
| LMArena Japanese | 1210 | 1299 |
| LMArena Korean | 1206 | 1304 |
| LMArena Russian | 1263 | 1353 |
| LMArena Spanish | 1283 | 1377 |
Instruction Following Qwen2.5-Max leads
Mistral Small 3.1: 63.8 (#225), Qwen2.5-Max: 71.5 (#147)
| Benchmark | Mistral Small 3.1 | Qwen2.5-Max |
|---|---|---|
| LMArena Instruction Following | 1264 | 1335 |
| LiveBench Instruction Following | — | 75.3% |
| IFEval | 75% | — |
Long Context Qwen2.5-Max leads
Mistral Small 3.1: 39.5 (#172), Qwen2.5-Max: 41.3 (#137)
| Benchmark | Mistral Small 3.1 | Qwen2.5-Max |
|---|---|---|
| LMArena Longer Query | 1300 | 1358 |
Writing & Preference Qwen2.5-Max leads
Mistral Small 3.1: 37.2 (#254), Qwen2.5-Max: 55.6 (#141)
| Benchmark | Mistral Small 3.1 | Qwen2.5-Max |
|---|---|---|
| LMArena Text | 1278 | 1367 |
| LMArena Creative Writing | 1253 | 1339 |
| LMArena Multi-Turn | 1270 | 1364 |
| Short-Story Creative Writing | — | 72.9% |
| EQ-Bench Creative Writing | 761 | — |
| WildBench | 78.8% | — |
| LiveBench Language | — | 56.3% |
Frequently asked questions
Is Mistral Small 3.1 better than Qwen2.5-Max?
Qwen2.5-Max is the stronger model overall, scoring 40.1 to 31.4 on the Noometry Index.
Is Mistral Small 3.1 or Qwen2.5-Max better for coding?
Qwen2.5-Max scores higher on coding benchmarks: 41.2 versus 37.7 in the Noometry coding category.
How many benchmarks do Mistral Small 3.1 and Qwen2.5-Max share?
18 benchmarks have published results for both models. Mistral Small 3.1 has 28 scored results on Noometry and Qwen2.5-Max has 27.