Model comparison
Mistral Large vs Qwen3 32B
Qwen3 32B is the stronger model overall, scoring 39.2 to 31.9 on the Noometry Index.
Last verified . 22 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 22 benchmarks with published results for both. Mistral Large scores higher in 0 categories and Qwen3 32B in 9 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3 32B leads 39.7 to 18.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 8.5% for Mistral Large and 66.9% for Qwen3 32B.
- Qwen3 32B is cheaper at $0.70 / $2.80 per million input/output tokens, against $2 / $6 for Mistral Large.
Side by side
| Mistral Large | Qwen3 32B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 31.9 | 39.2 |
| Released | 2024-02-26 | 2025-04 |
| Weights | Open | Open |
| Context window | 131K | 131K |
| Max output | 16K | 16K |
| Input $ / M tokens | $2 | $0.70 |
| Output $ / M tokens | $6 | $2.80 |
| Results tracked | 51 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 32B leads
Mistral Large: 34.3 (#240), Qwen3 32B: 37.7 (#190)
| Benchmark | Mistral Large | Qwen3 32B |
|---|---|---|
| SciCode | 36.2% | 35.4% |
| LMArena Coding | 1277 | 1358 |
| Aider Polyglot | — | 40% |
| BigCodeBench Instruct | 30% | — |
| LiveBench Coding | 47.1% | — |
| BigCodeBench Complete | 38.3% | — |
| ALE-Bench | 264.7 | — |
| HumanEval+ | 62.2% | — |
| MBPP+ | 59.5% | — |
Agentic & Tool Use Qwen3 32B leads
Mistral Large: 28.6 (#89), Qwen3 32B: 32.6 (#62)
| Benchmark | Mistral Large | Qwen3 32B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 38.4% | 48.7% |
Reasoning Qwen3 32B leads
Mistral Large: 15.8 (#310), Qwen3 32B: 20.2 (#241)
| Benchmark | Mistral Large | Qwen3 32B |
|---|---|---|
| CritPt | 0% | 0.3% |
| LMArena Hard Prompts | 1257 | 1334 |
| DTBench | 65.1% | 67.5% |
| LMCA | 16.7% | 17.3% |
| Epoch Capabilities Index | 128.52 | 138.51 |
| SimpleBench | 22.5% | — |
| Kagi LLM Benchmark | — | 54.9% |
| Chess Puzzles | — | 5% |
| LiveBench Reasoning | 43.5% | — |
| LiveBench Data Analysis | 50.1% | — |
| ForecastBench | 57.1 | — |
| LiveBench | 48.4% | — |
Math Qwen3 32B leads
Mistral Large: 18.2 (#291), Qwen3 32B: 39.7 (#99)
| Benchmark | Mistral Large | Qwen3 32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | 66.9% |
| LMArena Math | 1262 | 1399 |
| Omni-MATH | 28.1% | — |
| LiveBench Math | 42.5% | — |
| MATH Level 5 | 50.3% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Qwen3 32B leads
Mistral Large: 30.1 (#230), Qwen3 32B: 40.0 (#125)
| Benchmark | Mistral Large | Qwen3 32B |
|---|---|---|
| GPQA Diamond | 51.3% | 65.7% |
| Vectara Hallucination Rate | 4.5% | 5.9% |
| LMArena Expert | 1232 | 1362 |
| MMLU-Pro | 59.9% | — |
| Confabulations | 21.4% | — |
| GPQA (HELM) | 43.5% | — |
| MMLU | 80% | — |
Multilingual Qwen3 32B leads
Mistral Large: 40.0 (#219), Qwen3 32B: 45.6 (#167)
| Benchmark | Mistral Large | Qwen3 32B |
|---|---|---|
| LMArena Non-English | 1237 | 1317 |
| LMArena Chinese | 1240 | 1357 |
| LMArena German | 1254 | 1341 |
| LMArena Russian | 1257 | 1311 |
| LMArena French | 1325 | — |
| LMArena Japanese | 1188 | — |
| LMArena Korean | 1202 | — |
| LMArena Spanish | 1268 | — |
Instruction Following Too close to call
Mistral Large: 67.9 (#191), Qwen3 32B: 68.9 (#179)
| Benchmark | Mistral Large | Qwen3 32B |
|---|---|---|
| LMArena Instruction Following | 1249 | 1305 |
| LiveBench Instruction Following | 67.9% | — |
| IFEval | 87.7% | — |
Long Context Qwen3 32B leads
Mistral Large: 38.3 (#199), Qwen3 32B: 43.8 (#87)
| Benchmark | Mistral Large | Qwen3 32B |
|---|---|---|
| LMArena Longer Query | 1261 | 1327 |
| Fiction.LiveBench | — | 74.2% |
Writing & Preference Qwen3 32B leads
Mistral Large: 40.7 (#242), Qwen3 32B: 52.9 (#163)
| Benchmark | Mistral Large | Qwen3 32B |
|---|---|---|
| LMArena Text | 1266 | 1340 |
| LMArena Creative Writing | 1243 | 1297 |
| LMArena Multi-Turn | 1260 | 1331 |
| Short-Story Creative Writing | 69% | — |
| EQ-Bench Creative Writing | 985 | — |
| WildBench | 80.1% | — |
| LiveBench Language | 39.4% | — |
Frequently asked questions
Is Mistral Large better than Qwen3 32B?
Qwen3 32B is the stronger model overall, scoring 39.2 to 31.9 on the Noometry Index.
Which is cheaper, Mistral Large or Qwen3 32B?
Qwen3 32B is cheaper. It lists at $0.70 per million input tokens and $2.80 per million output tokens; Mistral Large lists at $2 and $6.
Is Mistral Large or Qwen3 32B better for coding?
Qwen3 32B scores higher on coding benchmarks: 37.7 versus 34.3 in the Noometry coding category.
Which has the bigger context window?
Both accept 131K tokens.
How many benchmarks do Mistral Large and Qwen3 32B share?
22 benchmarks have published results for both models. Mistral Large has 51 scored results on Noometry and Qwen3 32B has 26.