Model comparison
Mistral Small 3 vs Qwen3.5 Max Preview
Qwen3.5 Max Preview is the stronger model overall, scoring 44.7 to 30.9 on the Noometry Index.
Last verified . 16 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 16 benchmarks with published results for both. Mistral Small 3 scores higher in 0 categories and Qwen3.5 Max Preview in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3.5 Max Preview leads 66.1 to 32.4.
- Mistral Small 3 has downloadable open weights; the other is API-only.
Side by side
| Mistral Small 3 | Qwen3.5 Max Preview | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 30.9 | 44.7 |
| Released | 2025-01-30 | — |
| Weights | Open | Proprietary |
| Context window | 33K | — |
| Max output | 16K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.08 | — |
| Results tracked | 24 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.5 Max Preview leads
Mistral Small 3: 36.0 (#203), Qwen3.5 Max Preview: 43.4 (#79)
| Benchmark | Mistral Small 3 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Coding | 1246 | 1488 |
| BigCodeBench Instruct | 45.3% | — |
| BigCodeBench Complete | 50.4% | — |
Reasoning Qwen3.5 Max Preview leads
Mistral Small 3: 18.2 (#269), Qwen3.5 Max Preview: 29.6 (#81)
| Benchmark | Mistral Small 3 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Hard Prompts | 1233 | 1483 |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 127.06 | — |
Math Qwen3.5 Max Preview leads
Mistral Small 3: 15.3 (#290), Qwen3.5 Max Preview: 37.3 (#99)
| Benchmark | Mistral Small 3 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Math | 1240 | 1473 |
| OTIS Mock AIME 2024-2025 | 6.7% | — |
Knowledge Qwen3.5 Max Preview leads
Mistral Small 3: 25.0 (#258), Qwen3.5 Max Preview: 41.1 (#104)
| Benchmark | Mistral Small 3 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Expert | 1202 | 1489 |
| GPQA Diamond | 47.3% | — |
| Confabulations | 25.2% | — |
Multilingual Qwen3.5 Max Preview leads
Mistral Small 3: 37.5 (#231), Qwen3.5 Max Preview: 56.4 (#21)
| Benchmark | Mistral Small 3 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Non-English | 1198 | 1465 |
| LMArena Chinese | 1204 | 1534 |
| LMArena French | 1202 | 1483 |
| LMArena German | 1211 | 1487 |
| LMArena Japanese | 1111 | 1497 |
| LMArena Korean | 1188 | 1438 |
| LMArena Russian | 1216 | 1472 |
| LMArena Spanish | — | 1470 |
Instruction Following Qwen3.5 Max Preview leads
Mistral Small 3: 63.9 (#224), Qwen3.5 Max Preview: 77.2 (#28)
| Benchmark | Mistral Small 3 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Instruction Following | 1214 | 1467 |
Long Context Qwen3.5 Max Preview leads
Mistral Small 3: 37.8 (#206), Qwen3.5 Max Preview: 45.2 (#44)
| Benchmark | Mistral Small 3 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Longer Query | 1246 | 1477 |
Writing & Preference Qwen3.5 Max Preview leads
Mistral Small 3: 32.4 (#275), Qwen3.5 Max Preview: 66.1 (#39)
| Benchmark | Mistral Small 3 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Text | 1234 | 1471 |
| LMArena Creative Writing | 1195 | 1464 |
| LMArena Multi-Turn | 1217 | 1478 |
| EQ-Bench Creative Writing | 707 | — |
Frequently asked questions
Is Mistral Small 3 better than Qwen3.5 Max Preview?
Qwen3.5 Max Preview is the stronger model overall, scoring 44.7 to 30.9 on the Noometry Index.
Is Mistral Small 3 or Qwen3.5 Max Preview better for coding?
Qwen3.5 Max Preview scores higher on coding benchmarks: 43.4 versus 36.0 in the Noometry coding category.
How many benchmarks do Mistral Small 3 and Qwen3.5 Max Preview share?
16 benchmarks have published results for both models. Mistral Small 3 has 24 scored results on Noometry and Qwen3.5 Max Preview has 17.