Model comparison
Mistral Small 3 vs Qwen2.5-Max
Qwen2.5-Max is the stronger model overall, scoring 40.7 to 31.2 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 scores higher in 0 categories and Qwen2.5-Max in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen2.5-Max leads 55.4 to 32.2.
- Mistral Small 3 has downloadable open weights; the other is API-only.
Side by side
| Mistral Small 3 | Qwen2.5-Max | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 31.2 | 40.7 |
| Released | 2025-01-30 | 2025-01-25 |
| Weights | Open | Proprietary |
| Context window | 33K | — |
| Max output | 16K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.08 | — |
| Results tracked | 24 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5-Max leads
Mistral Small 3: 36.5 (#207), Qwen2.5-Max: 41.8 (#117)
| Benchmark | Mistral Small 3 | Qwen2.5-Max |
|---|---|---|
| LMArena Coding | 1246 | 1359 |
| BigCodeBench Instruct | 45.3% | — |
| LiveBench Coding | — | 64.4% |
| BigCodeBench Complete | 50.4% | — |
Reasoning Qwen2.5-Max leads
Mistral Small 3: 18.9 (#273), Qwen2.5-Max: 25.6 (#147)
| Benchmark | Mistral Small 3 | Qwen2.5-Max |
|---|---|---|
| LMArena Hard Prompts | 1233 | 1360 |
| Epoch Capabilities Index | 127.07 | 132.53 |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | — | 51.4% |
| LiveBench Data Analysis | — | 67.9% |
| LiveBench | — | 62.3% |
Math Qwen2.5-Max leads
Mistral Small 3: 16.3 (#295), Qwen2.5-Max: 36.9 (#162)
| Benchmark | Mistral Small 3 | Qwen2.5-Max |
|---|---|---|
| LMArena Math | 1240 | 1369 |
| OTIS Mock AIME 2024-2025 | 6.7% | — |
| LiveBench Math | — | 58.4% |
Knowledge Qwen2.5-Max leads
Mistral Small 3: 25.1 (#263), Qwen2.5-Max: 35.3 (#186)
| Benchmark | Mistral Small 3 | Qwen2.5-Max |
|---|---|---|
| Confabulations | 25.2% | 21.8% |
| LMArena Expert | 1202 | 1337 |
| GPQA Diamond | 47.3% | — |
Multilingual Qwen2.5-Max leads
Mistral Small 3: 37.3 (#236), Qwen2.5-Max: 48.1 (#146)
| Benchmark | Mistral Small 3 | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | 1198 | 1352 |
| LMArena Chinese | 1204 | 1382 |
| LMArena French | 1203 | 1396 |
| LMArena German | 1211 | 1350 |
| LMArena Japanese | 1111 | 1300 |
| LMArena Korean | 1188 | 1304 |
| LMArena Russian | 1216 | 1353 |
| LMArena Spanish | — | 1377 |
Instruction Following Qwen2.5-Max leads
Mistral Small 3: 63.7 (#229), Qwen2.5-Max: 71.3 (#152)
| Benchmark | Mistral Small 3 | Qwen2.5-Max |
|---|---|---|
| LMArena Instruction Following | 1214 | 1335 |
| LiveBench Instruction Following | — | 75.3% |
Long Context Qwen2.5-Max leads
Mistral Small 3: 37.8 (#211), Qwen2.5-Max: 41.4 (#142)
| Benchmark | Mistral Small 3 | Qwen2.5-Max |
|---|---|---|
| LMArena Longer Query | 1246 | 1358 |
Writing & Preference Qwen2.5-Max leads
Mistral Small 3: 32.2 (#280), Qwen2.5-Max: 55.4 (#146)
| Benchmark | Mistral Small 3 | Qwen2.5-Max |
|---|---|---|
| LMArena Text | 1234 | 1367 |
| LMArena Creative Writing | 1195 | 1339 |
| LMArena Multi-Turn | 1217 | 1364 |
| Short-Story Creative Writing | — | 72.9% |
| EQ-Bench Creative Writing | 707 | — |
| LiveBench Language | — | 56.3% |
Frequently asked questions
Is Mistral Small 3 better than Qwen2.5-Max?
Qwen2.5-Max is the stronger model overall, scoring 40.7 to 31.2 on the Noometry Index.
Is Mistral Small 3 or Qwen2.5-Max better for coding?
Qwen2.5-Max scores higher on coding benchmarks: 41.8 versus 36.5 in the Noometry coding category.
How many benchmarks do Mistral Small 3 and Qwen2.5-Max share?
18 benchmarks have published results for both models. Mistral Small 3 has 24 scored results on Noometry and Qwen2.5-Max has 27.