Model comparison
Mistral Large vs Qwen3 Max
Qwen3 Max is the stronger model overall, scoring 43.7 to 31.9 on the Noometry Index.
Last verified . 24 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 24 benchmarks with published results for both. Mistral Large scores higher in 0 categories and Qwen3 Max in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3 Max leads 62.4 to 40.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 8.5% for Mistral Large and 73.3% for Qwen3 Max.
- Qwen3 Max is cheaper at $1.20 / $6 per million input/output tokens, against $2 / $6 for Mistral Large.
- Qwen3 Max accepts more context: 262K tokens versus 131K.
- Mistral Large has downloadable open weights; the other is API-only.
Side by side
| Mistral Large | Qwen3 Max | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 31.9 | 43.7 |
| Released | 2024-02-26 | 2025-09-23 |
| Weights | Open | Proprietary |
| Context window | 131K | 262K |
| Max output | 16K | 66K |
| Input $ / M tokens | $2 | $1.20 |
| Output $ / M tokens | $6 | $6 |
| Results tracked | 51 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 Max leads
Mistral Large: 34.3 (#240), Qwen3 Max: 43.0 (#93)
| Benchmark | Mistral Large | Qwen3 Max |
|---|---|---|
| LMArena Coding | 1277 | 1456 |
| ALE-Bench | 264.7 | 370.45 |
| SciCode | 36.2% | — |
| BigCodeBench Instruct | 30% | — |
| LiveBench Coding | 47.1% | — |
| BigCodeBench Complete | 38.3% | — |
| HumanEval+ | 62.2% | — |
| MBPP+ | 59.5% | — |
Agentic & Tool Use Not comparable
Mistral Large: 28.6 (#89), Qwen3 Max: —
| Benchmark | Mistral Large | Qwen3 Max |
|---|---|---|
| Berkeley Function Calling Leaderboard | 38.4% | — |
| Vending-Bench 2 | — | 71.56 |
Reasoning Qwen3 Max leads
Mistral Large: 15.8 (#310), Qwen3 Max: 22.6 (#190)
| Benchmark | Mistral Large | Qwen3 Max |
|---|---|---|
| LMArena Hard Prompts | 1257 | 1448 |
| DTBench | 65.1% | 82.1% |
| LMCA | 16.7% | 28.3% |
| Epoch Capabilities Index | 128.52 | 142.38 |
| SimpleBench | 22.5% | — |
| Kagi LLM Benchmark | — | 72.5% |
| NYT Connections (extended) | — | 30.1% |
| CritPt | 0% | — |
| Chess Puzzles | — | 4% |
| LiveBench Reasoning | 43.5% | — |
| Mystery Game Puzzles | — | 5% |
| LiveBench Data Analysis | 50.1% | — |
| ForecastBench | 57.1 | — |
| LiveBench | 48.4% | — |
Math Qwen3 Max leads
Mistral Large: 18.2 (#291), Qwen3 Max: 38.7 (#131)
| Benchmark | Mistral Large | Qwen3 Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | 73.3% |
| LMArena Math | 1262 | 1446 |
| MATH Level 5 | 50.3% | 97.1% |
| FrontierMath (Tiers 1-3) | — | 18.9% |
| Omni-MATH | 28.1% | — |
| LiveBench Math | 42.5% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Qwen3 Max leads
Mistral Large: 30.1 (#230), Qwen3 Max: 48.1 (#78)
| Benchmark | Mistral Large | Qwen3 Max |
|---|---|---|
| GPQA Diamond | 51.3% | 72.6% |
| LMArena Expert | 1232 | 1455 |
| SimpleQA Verified | — | 48.7% |
| MMLU-Pro | 59.9% | — |
| Confabulations | 21.4% | — |
| Vectara Hallucination Rate | 4.5% | — |
| GPQA (HELM) | 43.5% | — |
| MMLU | 80% | — |
Multilingual Qwen3 Max leads
Mistral Large: 40.0 (#219), Qwen3 Max: 53.7 (#62)
| Benchmark | Mistral Large | Qwen3 Max |
|---|---|---|
| LMArena Non-English | 1237 | 1429 |
| LMArena Chinese | 1240 | 1478 |
| LMArena French | 1325 | 1449 |
| LMArena German | 1254 | 1463 |
| LMArena Japanese | 1188 | 1397 |
| LMArena Korean | 1202 | 1399 |
| LMArena Russian | 1257 | 1428 |
| LMArena Spanish | 1268 | 1462 |
Instruction Following Qwen3 Max leads
Mistral Large: 67.9 (#191), Qwen3 Max: 74.8 (#87)
| Benchmark | Mistral Large | Qwen3 Max |
|---|---|---|
| LMArena Instruction Following | 1249 | 1419 |
| LiveBench Instruction Following | 67.9% | — |
| IFEval | 87.7% | — |
Long Context Qwen3 Max leads
Mistral Large: 38.3 (#199), Qwen3 Max: 41.6 (#134)
| Benchmark | Mistral Large | Qwen3 Max |
|---|---|---|
| LMArena Longer Query | 1261 | 1438 |
| Fiction.LiveBench | — | 66.7% |
| CL-bench | — | 14.5% |
Writing & Preference Qwen3 Max leads
Mistral Large: 40.7 (#242), Qwen3 Max: 62.4 (#76)
| Benchmark | Mistral Large | Qwen3 Max |
|---|---|---|
| LMArena Text | 1266 | 1439 |
| LMArena Creative Writing | 1243 | 1402 |
| LMArena Multi-Turn | 1260 | 1446 |
| 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 Max?
Qwen3 Max is the stronger model overall, scoring 43.7 to 31.9 on the Noometry Index.
Which is cheaper, Mistral Large or Qwen3 Max?
Qwen3 Max is cheaper. It lists at $1.20 per million input tokens and $6 per million output tokens; Mistral Large lists at $2 and $6.
Is Mistral Large or Qwen3 Max better for coding?
Qwen3 Max scores higher on coding benchmarks: 43.0 versus 34.3 in the Noometry coding category.
Which has the bigger context window?
Qwen3 Max does, with 262K tokens against 131K.
How many benchmarks do Mistral Large and Qwen3 Max share?
24 benchmarks have published results for both models. Mistral Large has 51 scored results on Noometry and Qwen3 Max has 33.