Model comparison
Mistral Large vs Qwen Max
Qwen Max is the stronger model overall, scoring 34.7 to 31.9 on the Noometry Index.
Last verified . 21 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 21 benchmarks with published results for both. Mistral Large scores higher in 2 categories and Qwen Max in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen Max leads 25.1 to 15.8.
- The biggest single-benchmark swing is MATH Level 5: 50.3% for Mistral Large and 67.2% for Qwen Max.
- Qwen Max is cheaper at $1.60 / $6.40 per million input/output tokens, against $2 / $6 for Mistral Large.
- Mistral Large accepts more context: 131K tokens versus 33K.
- Mistral Large has downloadable open weights; the other is API-only.
Side by side
| Mistral Large | Qwen Max | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 31.9 | 34.7 |
| Released | 2024-02-26 | 2024-04-03 |
| Weights | Open | Proprietary |
| Context window | 131K | 33K |
| Max output | 16K | 8K |
| Input $ / M tokens | $2 | $1.60 |
| Output $ / M tokens | $6 | $6.40 |
| Results tracked | 51 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Large leads
Mistral Large: 34.3 (#240), Qwen Max: 30.7 (#292)
| Benchmark | Mistral Large | Qwen Max |
|---|---|---|
| LMArena Coding | 1277 | 1288 |
| Aider Polyglot | — | 21.8% |
| SciCode | 36.2% | — |
| BigCodeBench Instruct | 30% | — |
| LiveBench Coding | 47.1% | — |
| BigCodeBench Complete | 38.3% | — |
| ALE-Bench | 264.7 | — |
| HumanEval+ | 62.2% | — |
| MBPP+ | 59.5% | — |
Agentic & Tool Use Not comparable
Mistral Large: 28.6 (#89), Qwen Max: —
| Benchmark | Mistral Large | Qwen Max |
|---|---|---|
| Berkeley Function Calling Leaderboard | 38.4% | — |
Reasoning Qwen Max leads
Mistral Large: 15.8 (#310), Qwen Max: 25.1 (#151)
| Benchmark | Mistral Large | Qwen Max |
|---|---|---|
| LMArena Hard Prompts | 1257 | 1269 |
| SimpleBench | 22.5% | — |
| CritPt | 0% | — |
| LiveBench Reasoning | 43.5% | — |
| DTBench | 65.1% | — |
| LiveBench Data Analysis | 50.1% | — |
| LMCA | 16.7% | — |
| Epoch Capabilities Index | 128.52 | — |
| ForecastBench | 57.1 | — |
| LiveBench | 48.4% | — |
Math Qwen Max leads
Mistral Large: 18.2 (#291), Qwen Max: 22.3 (#276)
| Benchmark | Mistral Large | Qwen Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | 16.1% |
| LMArena Math | 1262 | 1275 |
| MATH Level 5 | 50.3% | 67.2% |
| FrontierMath (Feb 2025 set) | 0.3% | 1% |
| Omni-MATH | 28.1% | — |
| LiveBench Math | 42.5% | — |
Knowledge Too close to call
Mistral Large: 30.1 (#230), Qwen Max: 30.3 (#228)
| Benchmark | Mistral Large | Qwen Max |
|---|---|---|
| GPQA Diamond | 51.3% | 56.1% |
| LMArena Expert | 1232 | 1248 |
| MMLU-Pro | 59.9% | — |
| Confabulations | 21.4% | — |
| Vectara Hallucination Rate | 4.5% | — |
| GPQA (HELM) | 43.5% | — |
| MMLU | 80% | — |
Multilingual Qwen Max leads
Mistral Large: 40.0 (#219), Qwen Max: 41.8 (#202)
| Benchmark | Mistral Large | Qwen Max |
|---|---|---|
| LMArena Non-English | 1237 | 1263 |
| LMArena Chinese | 1240 | 1254 |
| LMArena French | 1325 | 1330 |
| LMArena German | 1254 | 1254 |
| LMArena Japanese | 1188 | 1205 |
| LMArena Korean | 1202 | 1142 |
| LMArena Russian | 1257 | 1274 |
| LMArena Spanish | 1268 | 1290 |
Instruction Following Mistral Large leads
Mistral Large: 67.9 (#191), Qwen Max: 66.5 (#208)
| Benchmark | Mistral Large | Qwen Max |
|---|---|---|
| LMArena Instruction Following | 1249 | 1262 |
| LiveBench Instruction Following | 67.9% | — |
| IFEval | 87.7% | — |
Long Context Qwen Max leads
Mistral Large: 38.3 (#199), Qwen Max: 39.4 (#180)
| Benchmark | Mistral Large | Qwen Max |
|---|---|---|
| LMArena Longer Query | 1261 | 1288 |
| Fiction.LiveBench | — | 66.7% |
Writing & Preference Qwen Max leads
Mistral Large: 40.7 (#242), Qwen Max: 47.8 (#205)
| Benchmark | Mistral Large | Qwen Max |
|---|---|---|
| LMArena Text | 1266 | 1282 |
| LMArena Creative Writing | 1243 | 1248 |
| LMArena Multi-Turn | 1260 | 1277 |
| 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 Qwen Max?
Qwen Max is the stronger model overall, scoring 34.7 to 31.9 on the Noometry Index.
Which is cheaper, Mistral Large or Qwen Max?
Qwen Max is cheaper. It lists at $1.60 per million input tokens and $6.40 per million output tokens; Mistral Large lists at $2 and $6.
Is Mistral Large or Qwen Max better for coding?
Mistral Large scores higher on coding benchmarks: 34.3 versus 30.7 in the Noometry coding category.
Which has the bigger context window?
Mistral Large does, with 131K tokens against 33K.
How many benchmarks do Mistral Large and Qwen Max share?
21 benchmarks have published results for both models. Mistral Large has 51 scored results on Noometry and Qwen Max has 23.