Model comparison
Mistral Small vs Qwen3 32B
Qwen3 32B is the stronger model overall, scoring 39.2 to 33.4 on the Noometry Index. Mistral Small costs 4.7× less per token, which makes it the better buy when Qwen3 32B's lead doesn't matter for your workload.
Last verified . 22 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 22 benchmarks with published results for both. Mistral Small scores higher in 0 categories and Qwen3 32B in 9 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3 32B leads 39.7 to 16.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 5.8% for Mistral Small and 66.9% for Qwen3 32B.
- Mistral Small is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.70 / $2.80 for Qwen3 32B.
- Mistral Small accepts more context: 262K tokens versus 131K.
Side by side
| Mistral Small | Qwen3 32B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 33.4 | 39.2 |
| Released | 2024-02-26 | 2025-04 |
| Weights | Open | Open |
| Context window | 262K | 131K |
| Max output | 256K | 16K |
| Input $ / M tokens | $0.15 | $0.70 |
| Output $ / M tokens | $0.60 | $2.80 |
| Results tracked | 39 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 32B leads
Mistral Small: 34.0 (#247), Qwen3 32B: 37.7 (#190)
| Benchmark | Mistral Small | Qwen3 32B |
|---|---|---|
| SciCode | 26.5% | 35.4% |
| LMArena Coding | 1362 | 1358 |
| Aider Polyglot | — | 40% |
| BigCodeBench Instruct | 36.1% | — |
| LiveBench Coding | 36.2% | — |
| BigCodeBench Complete | 46.6% | — |
| ALE-Bench | 497.62 | — |
Agentic & Tool Use Qwen3 32B leads
Mistral Small: 28.1 (#93), Qwen3 32B: 32.6 (#62)
| Benchmark | Mistral Small | Qwen3 32B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.1% | 48.7% |
Reasoning Too close to call
Mistral Small: 19.8 (#250), Qwen3 32B: 20.2 (#241)
| Benchmark | Mistral Small | Qwen3 32B |
|---|---|---|
| Kagi LLM Benchmark | 37.8% | 54.9% |
| CritPt | 0% | 0.3% |
| LMArena Hard Prompts | 1335 | 1334 |
| DTBench | 70.9% | 67.5% |
| LMCA | 20.6% | 17.3% |
| Chess Puzzles | — | 5% |
| LiveBench Reasoning | 44.8% | — |
| LiveBench Data Analysis | 53.7% | — |
| Epoch Capabilities Index | — | 138.51 |
| LiveBench | 44% | — |
Math Qwen3 32B leads
Mistral Small: 16.4 (#293), Qwen3 32B: 39.7 (#99)
| Benchmark | Mistral Small | Qwen3 32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 5.8% | 66.9% |
| LMArena Math | 1341 | 1399 |
| LiveBench Math | 39.9% | — |
| MATH Level 5 | 46.8% | — |
Knowledge Qwen3 32B leads
Mistral Small: 31.0 (#222), Qwen3 32B: 40.0 (#125)
| Benchmark | Mistral Small | Qwen3 32B |
|---|---|---|
| GPQA Diamond | 47.5% | 65.7% |
| Vectara Hallucination Rate | 5.1% | 5.9% |
| LMArena Expert | 1291 | 1362 |
| MMLU | 68.7% | — |
Multimodal Not comparable
Mistral Small: 33.5 (#96), Qwen3 32B: —
| Benchmark | Mistral Small | Qwen3 32B |
|---|---|---|
| LMArena Vision | 1142 | — |
Multilingual Too close to call
Mistral Small: 45.5 (#169), Qwen3 32B: 45.6 (#167)
| Benchmark | Mistral Small | Qwen3 32B |
|---|---|---|
| LMArena Non-English | 1315 | 1317 |
| LMArena Chinese | 1340 | 1357 |
| LMArena German | 1340 | 1341 |
| LMArena Russian | 1324 | 1311 |
| LMArena French | 1337 | — |
| LMArena Japanese | 1275 | — |
| LMArena Korean | 1259 | — |
| LMArena Spanish | 1346 | — |
Instruction Following Qwen3 32B leads
Mistral Small: 66.4 (#209), Qwen3 32B: 68.9 (#179)
| Benchmark | Mistral Small | Qwen3 32B |
|---|---|---|
| LMArena Instruction Following | 1310 | 1305 |
| LiveBench Instruction Following | 63.7% | — |
Long Context Qwen3 32B leads
Mistral Small: 40.4 (#156), Qwen3 32B: 43.8 (#87)
| Benchmark | Mistral Small | Qwen3 32B |
|---|---|---|
| LMArena Longer Query | 1327 | 1327 |
| Fiction.LiveBench | — | 74.2% |
Writing & Preference Too close to call
Mistral Small: 52.5 (#171), Qwen3 32B: 52.9 (#163)
| Benchmark | Mistral Small | Qwen3 32B |
|---|---|---|
| LMArena Text | 1338 | 1340 |
| LMArena Creative Writing | 1305 | 1297 |
| LMArena Multi-Turn | 1344 | 1331 |
| LiveBench Language | 30.5% | — |
Frequently asked questions
Is Mistral Small better than Qwen3 32B?
Qwen3 32B is the stronger model overall, scoring 39.2 to 33.4 on the Noometry Index. Mistral Small costs 4.7× 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 or Qwen3 32B?
Mistral Small is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Qwen3 32B lists at $0.70 and $2.80.
Is Mistral Small or Qwen3 32B better for coding?
Qwen3 32B scores higher on coding benchmarks: 37.7 versus 34.0 in the Noometry coding category.
Which has the bigger context window?
Mistral Small does, with 262K tokens against 131K.
How many benchmarks do Mistral Small and Qwen3 32B share?
22 benchmarks have published results for both models. Mistral Small has 39 scored results on Noometry and Qwen3 32B has 26.