Model comparison
Mistral Small 3.1 vs Qwen1.5-32B
Mistral Small 3.1 is the stronger model overall, scoring 31.4 to 30.0 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 6 categories and Qwen1.5-32B in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen1.5-32B leads 30.5 to 13.7.
- The biggest single-benchmark swing is GPQA Diamond: 41.9% for Mistral Small 3.1 and 30.7% for Qwen1.5-32B.
Side by side
| Mistral Small 3.1 | Qwen1.5-32B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 31.4 | 30.0 |
| Released | 2025-03-17 | 2024-02-04 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 102K | — |
| Input $ / M tokens | $0.35 | — |
| Output $ / M tokens | $0.56 | — |
| Results tracked | 28 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small 3.1 leads
Mistral Small 3.1: 37.7 (#175), Qwen1.5-32B: 31.1 (#278)
| Benchmark | Mistral Small 3.1 | Qwen1.5-32B |
|---|---|---|
| LMArena Coding | 1309 | 1155 |
| BigCodeBench Instruct | — | 32.3% |
| BigCodeBench Complete | — | 42% |
Reasoning Qwen1.5-32B leads
Mistral Small 3.1: 18.9 (#249), Qwen1.5-32B: 20.9 (#210)
| Benchmark | Mistral Small 3.1 | Qwen1.5-32B |
|---|---|---|
| LMArena Hard Prompts | 1278 | 1131 |
| Chess Puzzles | 1% | — |
| Epoch Capabilities Index | 127.48 | — |
Math Qwen1.5-32B leads
Mistral Small 3.1: 13.7 (#295), Qwen1.5-32B: 30.5 (#207)
| Benchmark | Mistral Small 3.1 | Qwen1.5-32B |
|---|---|---|
| LMArena Math | 1261 | 1155 |
| OTIS Mock AIME 2024-2025 | 3.9% | — |
| Omni-MATH | 24.8% | — |
Knowledge Mistral Small 3.1 leads
Mistral Small 3.1: 22.6 (#266), Qwen1.5-32B: 13.5 (#291)
| Benchmark | Mistral Small 3.1 | Qwen1.5-32B |
|---|---|---|
| GPQA Diamond | 41.9% | 30.7% |
| LMArena Expert | 1258 | 1126 |
| MMLU-Pro | 61% | — |
| GPQA (HELM) | 39.2% | — |
| MMLU | — | 74.4% |
Multimodal Not comparable
Mistral Small 3.1: 32.6 (#93), Qwen1.5-32B: —
| Benchmark | Mistral Small 3.1 | Qwen1.5-32B |
|---|---|---|
| LMArena Vision | 1136 | — |
Multilingual Mistral Small 3.1 leads
Mistral Small 3.1: 41.4 (#204), Qwen1.5-32B: 31.6 (#254)
| Benchmark | Mistral Small 3.1 | Qwen1.5-32B |
|---|---|---|
| LMArena Non-English | 1255 | 1106 |
| LMArena Chinese | 1254 | 1176 |
| LMArena French | 1270 | 1100 |
| LMArena German | 1266 | 1058 |
| LMArena Japanese | 1210 | 1027 |
| LMArena Korean | 1206 | 1007 |
| LMArena Russian | 1263 | 1073 |
| LMArena Spanish | 1283 | 1089 |
Instruction Following Mistral Small 3.1 leads
Mistral Small 3.1: 63.8 (#225), Qwen1.5-32B: 58.0 (#260)
| Benchmark | Mistral Small 3.1 | Qwen1.5-32B |
|---|---|---|
| LMArena Instruction Following | 1264 | 1116 |
| IFEval | 75% | — |
Long Context Mistral Small 3.1 leads
Mistral Small 3.1: 39.5 (#172), Qwen1.5-32B: 34.7 (#241)
| Benchmark | Mistral Small 3.1 | Qwen1.5-32B |
|---|---|---|
| LMArena Longer Query | 1300 | 1146 |
Writing & Preference Mistral Small 3.1 leads
Mistral Small 3.1: 37.2 (#254), Qwen1.5-32B: 34.4 (#266)
| Benchmark | Mistral Small 3.1 | Qwen1.5-32B |
|---|---|---|
| LMArena Text | 1278 | 1137 |
| LMArena Creative Writing | 1253 | 1083 |
| LMArena Multi-Turn | 1270 | 1140 |
| EQ-Bench Creative Writing | 761 | — |
| WildBench | 78.8% | — |
Frequently asked questions
Is Mistral Small 3.1 better than Qwen1.5-32B?
Mistral Small 3.1 is the stronger model overall, scoring 31.4 to 30.0 on the Noometry Index.
Is Mistral Small 3.1 or Qwen1.5-32B better for coding?
Mistral Small 3.1 scores higher on coding benchmarks: 37.7 versus 31.1 in the Noometry coding category.
How many benchmarks do Mistral Small 3.1 and Qwen1.5-32B share?
18 benchmarks have published results for both models. Mistral Small 3.1 has 28 scored results on Noometry and Qwen1.5-32B has 21.