Model comparison
Mistral Small 3.1 vs Qwen3 32B
Qwen3 32B is the stronger model overall, scoring 39.2 to 31.7 on the Noometry Index. Mistral Small 3.1 costs 3.0× less per token, which makes it the better buy when Qwen3 32B's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Mistral Small 3.1 scores higher in 1 category and Qwen3 32B in 7 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3 32B leads 39.7 to 14.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 3.9% for Mistral Small 3.1 and 66.9% for Qwen3 32B.
- Mistral Small 3.1 is cheaper at $0.35 / $0.56 per million input/output tokens, against $0.70 / $2.80 for Qwen3 32B.
- Qwen3 32B accepts more context: 131K tokens versus 128K.
Side by side
| Mistral Small 3.1 | Qwen3 32B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 31.7 | 39.2 |
| Released | 2025-03-17 | 2025-04 |
| Weights | Open | Open |
| Context window | 128K | 131K |
| Max output | 102K | 16K |
| Input $ / M tokens | $0.35 | $0.70 |
| Output $ / M tokens | $0.56 | $2.80 |
| Results tracked | 28 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Mistral Small 3.1: 38.3 (#179), Qwen3 32B: 37.7 (#190)
| Benchmark | Mistral Small 3.1 | Qwen3 32B |
|---|---|---|
| LMArena Coding | 1309 | 1358 |
| Aider Polyglot | — | 40% |
| SciCode | — | 35.4% |
Agentic & Tool Use Not comparable
Mistral Small 3.1: —, Qwen3 32B: 32.6 (#62)
| Benchmark | Mistral Small 3.1 | Qwen3 32B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 48.7% |
Reasoning Too close to call
Mistral Small 3.1: 19.7 (#254), Qwen3 32B: 20.2 (#241)
| Benchmark | Mistral Small 3.1 | Qwen3 32B |
|---|---|---|
| Chess Puzzles | 1% | 5% |
| LMArena Hard Prompts | 1278 | 1334 |
| Epoch Capabilities Index | 127.48 | 138.51 |
| Kagi LLM Benchmark | — | 54.9% |
| CritPt | — | 0.3% |
| DTBench | — | 67.5% |
| LMCA | — | 17.3% |
Math Qwen3 32B leads
Mistral Small 3.1: 14.7 (#301), Qwen3 32B: 39.7 (#99)
| Benchmark | Mistral Small 3.1 | Qwen3 32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 3.9% | 66.9% |
| LMArena Math | 1262 | 1399 |
| Omni-MATH | 24.8% | — |
Knowledge Qwen3 32B leads
Mistral Small 3.1: 22.6 (#271), Qwen3 32B: 40.0 (#125)
| Benchmark | Mistral Small 3.1 | Qwen3 32B |
|---|---|---|
| GPQA Diamond | 41.9% | 65.7% |
| LMArena Expert | 1257 | 1362 |
| MMLU-Pro | 61% | — |
| Vectara Hallucination Rate | — | 5.9% |
| GPQA (HELM) | 39.2% | — |
Multimodal Not comparable
Mistral Small 3.1: 33.2 (#99), Qwen3 32B: —
| Benchmark | Mistral Small 3.1 | Qwen3 32B |
|---|---|---|
| LMArena Vision | 1136 | — |
Multilingual Qwen3 32B leads
Mistral Small 3.1: 41.2 (#209), Qwen3 32B: 45.6 (#167)
| Benchmark | Mistral Small 3.1 | Qwen3 32B |
|---|---|---|
| LMArena Non-English | 1255 | 1317 |
| LMArena Chinese | 1253 | 1357 |
| LMArena German | 1266 | 1341 |
| LMArena Russian | 1263 | 1311 |
| LMArena French | 1273 | — |
| LMArena Japanese | 1208 | — |
| LMArena Korean | 1206 | — |
| LMArena Spanish | 1283 | — |
Instruction Following Qwen3 32B leads
Mistral Small 3.1: 63.6 (#230), Qwen3 32B: 68.9 (#179)
| Benchmark | Mistral Small 3.1 | Qwen3 32B |
|---|---|---|
| LMArena Instruction Following | 1264 | 1305 |
| IFEval | 75% | — |
Long Context Qwen3 32B leads
Mistral Small 3.1: 39.5 (#178), Qwen3 32B: 43.8 (#87)
| Benchmark | Mistral Small 3.1 | Qwen3 32B |
|---|---|---|
| LMArena Longer Query | 1299 | 1327 |
| Fiction.LiveBench | — | 74.2% |
Writing & Preference Qwen3 32B leads
Mistral Small 3.1: 37.0 (#259), Qwen3 32B: 52.9 (#163)
| Benchmark | Mistral Small 3.1 | Qwen3 32B |
|---|---|---|
| LMArena Text | 1277 | 1340 |
| LMArena Creative Writing | 1253 | 1297 |
| LMArena Multi-Turn | 1270 | 1331 |
| EQ-Bench Creative Writing | 761 | — |
| WildBench | 78.8% | — |
Frequently asked questions
Is Mistral Small 3.1 better than Qwen3 32B?
Qwen3 32B is the stronger model overall, scoring 39.2 to 31.7 on the Noometry Index. Mistral Small 3.1 costs 3.0× less per token, which makes it the better buy when Qwen3 32B's lead doesn't matter for your workload.
Which is cheaper, Mistral Small 3.1 or Qwen3 32B?
Mistral Small 3.1 is cheaper. It lists at $0.35 per million input tokens and $0.56 per million output tokens; Qwen3 32B lists at $0.70 and $2.80.
Is Mistral Small 3.1 or Qwen3 32B better for coding?
They score almost the same on coding (38.3 vs 37.7); test both on your own repository before choosing.
Which has the bigger context window?
Qwen3 32B does, with 131K tokens against 128K.
How many benchmarks do Mistral Small 3.1 and Qwen3 32B share?
17 benchmarks have published results for both models. Mistral Small 3.1 has 28 scored results on Noometry and Qwen3 32B has 26.