Model comparison
Mistral Small 3.2 vs Qwen3 235B-A22B
Qwen3 235B-A22B is the stronger model overall, scoring 43.2 to 30.8 on the Noometry Index. Mistral Small 3.2 costs 9.2× less per token, which makes it the better buy when Qwen3 235B-A22B's lead doesn't matter for your workload.
Last verified . 6 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 6 benchmarks with published results for both. Mistral Small 3.2 scores higher in 1 category and Qwen3 235B-A22B in 3 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3 235B-A22B leads 48.5 to 24.9.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 30.3% for Mistral Small 3.2 and 86.7% for Qwen3 235B-A22B.
- Mistral Small 3.2 is cheaper at $0.0938 / $0.25 per million input/output tokens, against $0.70 / $2.80 for Qwen3 235B-A22B.
- Mistral Small 3.2 accepts more context: 256K tokens versus 131K.
Side by side
| Mistral Small 3.2 | Qwen3 235B-A22B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 30.8 | 43.2 |
| Released | 2025-06-20 | 2025-04 |
| Weights | Open | Open |
| Context window | 256K | 131K |
| Max output | 16K | 16K |
| Input $ / M tokens | $0.0938 | $0.70 |
| Output $ / M tokens | $0.25 | $2.80 |
| Results tracked | 6 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Mistral Small 3.2: —, Qwen3 235B-A22B: 43.8 (#72)
| Benchmark | Mistral Small 3.2 | Qwen3 235B-A22B |
|---|---|---|
| Aider Polyglot | — | 59.6% |
| SciCode | — | 42.4% |
| WeirdML | — | 41% |
| LMArena Coding | — | 1445 |
Agentic & Tool Use Not comparable
Mistral Small 3.2: —, Qwen3 235B-A22B: 33.7 (#48)
| Benchmark | Mistral Small 3.2 | Qwen3 235B-A22B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 52.1% |
| Vending-Bench 2 | — | -11.34 |
Reasoning Mistral Small 3.2 leads
Mistral Small 3.2: 17.5 (#282), Qwen3 235B-A22B: 15.8 (#302)
| Benchmark | Mistral Small 3.2 | Qwen3 235B-A22B |
|---|---|---|
| Kagi LLM Benchmark | 40.4% | 69.4% |
| Chess Puzzles | 1% | 12% |
| Epoch Capabilities Index | 131.73 | 143.87 |
| ARC-AGI-2 | — | 1.3% |
| SimpleBench | — | 31% |
| ARC-AGI-1 | — | 11% |
| CritPt | — | 0% |
| LMArena Hard Prompts | — | 1433 |
| Mystery Game Puzzles | — | 9% |
| DTBench | — | 80.3% |
| LMCA | — | 29.3% |
| ForecastBench | — | 59.7 |
Math Qwen3 235B-A22B leads
Mistral Small 3.2: 24.9 (#251), Qwen3 235B-A22B: 48.5 (#51)
| Benchmark | Mistral Small 3.2 | Qwen3 235B-A22B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 30.3% | 86.7% |
| Omni-MATH | — | 71.8% |
| LMArena Math | — | 1431 |
| MATH Level 5 | — | 68.9% |
| FrontierMath (Feb 2025 set) | — | 8.5% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Qwen3 235B-A22B leads
Mistral Small 3.2: 26.8 (#249), Qwen3 235B-A22B: 49.5 (#67)
| Benchmark | Mistral Small 3.2 | Qwen3 235B-A22B |
|---|---|---|
| GPQA Diamond | 49.1% | 80.1% |
| SimpleQA Verified | — | 40.4% |
| MMLU-Pro | — | 84.4% |
| Confabulations | — | 15.6% |
| Vectara Hallucination Rate | — | 9.3% |
| GPQA (HELM) | — | 72.7% |
| LMArena Expert | — | 1460 |
Multilingual Not comparable
Mistral Small 3.2: —, Qwen3 235B-A22B: 52.5 (#84)
| Benchmark | Mistral Small 3.2 | Qwen3 235B-A22B |
|---|---|---|
| LMArena Non-English | — | 1410 |
| LMArena Chinese | — | 1481 |
| LMArena French | — | 1445 |
| LMArena German | — | 1432 |
| LMArena Japanese | — | 1400 |
| LMArena Korean | — | 1391 |
| LMArena Russian | — | 1411 |
| LMArena Spanish | — | 1429 |
Instruction Following Not comparable
Mistral Small 3.2: —, Qwen3 235B-A22B: 72.8 (#132)
| Benchmark | Mistral Small 3.2 | Qwen3 235B-A22B |
|---|---|---|
| IFEval | — | 83.5% |
| LMArena Instruction Following | — | 1408 |
Long Context Not comparable
Mistral Small 3.2: —, Qwen3 235B-A22B: 46.1 (#25)
| Benchmark | Mistral Small 3.2 | Qwen3 235B-A22B |
|---|---|---|
| Fiction.LiveBench | — | 75% |
| LMArena Longer Query | — | 1426 |
Writing & Preference Qwen3 235B-A22B leads
Mistral Small 3.2: 45.1 (#219), Qwen3 235B-A22B: 59.8 (#103)
| Benchmark | Mistral Small 3.2 | Qwen3 235B-A22B |
|---|---|---|
| EQ-Bench Creative Writing | 1255 | 1366 |
| LMArena Text | — | 1419 |
| LMArena Creative Writing | — | 1384 |
| Short-Story Creative Writing | — | 83% |
| WildBench | — | 86.6% |
| LMArena Multi-Turn | — | 1432 |
Frequently asked questions
Is Mistral Small 3.2 better than Qwen3 235B-A22B?
Qwen3 235B-A22B is the stronger model overall, scoring 43.2 to 30.8 on the Noometry Index. Mistral Small 3.2 costs 9.2× less per token, which makes it the better buy when Qwen3 235B-A22B's lead doesn't matter for your workload.
Which is cheaper, Mistral Small 3.2 or Qwen3 235B-A22B?
Mistral Small 3.2 is cheaper. It lists at $0.0938 per million input tokens and $0.25 per million output tokens; Qwen3 235B-A22B lists at $0.70 and $2.80.
Which has the bigger context window?
Mistral Small 3.2 does, with 256K tokens against 131K.
How many benchmarks do Mistral Small 3.2 and Qwen3 235B-A22B share?
6 benchmarks have published results for both models. Mistral Small 3.2 has 6 scored results on Noometry and Qwen3 235B-A22B has 49.