Model comparison
Mistral Medium vs Qwen3 Max
Qwen3 Max is the stronger model overall, scoring 43.7 to 36.3 on the Noometry Index.
Last verified . 24 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 24 benchmarks with published results for both. Mistral Medium scores higher in 2 categories and Qwen3 Max in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3 Max leads 48.1 to 25.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 32.2% for Mistral Medium and 73.3% for Qwen3 Max.
- Qwen3 Max is cheaper at $1.20 / $6 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
- Mistral Medium has downloadable open weights; the other is API-only.
Side by side
| Mistral Medium | Qwen3 Max | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 36.3 | 43.7 |
| Released | 2023-12-11 | 2025-09-23 |
| Weights | Open | Proprietary |
| Context window | 262K | 262K |
| Max output | 262K | 66K |
| Input $ / M tokens | $1.50 | $1.20 |
| Output $ / M tokens | $7.50 | $6 |
| Results tracked | 36 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 Max leads
Mistral Medium: 34.2 (#243), Qwen3 Max: 43.0 (#93)
| Benchmark | Mistral Medium | Qwen3 Max |
|---|---|---|
| LMArena Coding | 1434 | 1456 |
| ALE-Bench | 763.98 | 370.45 |
| FrontierCode | 8% | — |
| SciCode | 40.2% | — |
| WeirdML | 43.7% | — |
Agentic & Tool Use Not comparable
Mistral Medium: 28.3 (#90), Qwen3 Max: —
| Benchmark | Mistral Medium | Qwen3 Max |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.7% | — |
| Vending-Bench 2 | — | 71.56 |
Reasoning Mistral Medium leads
Mistral Medium: 24.0 (#167), Qwen3 Max: 22.6 (#190)
| Benchmark | Mistral Medium | Qwen3 Max |
|---|---|---|
| Kagi LLM Benchmark | 50% | 72.5% |
| LMArena Hard Prompts | 1426 | 1448 |
| DTBench | 75.5% | 82.1% |
| LMCA | 26.1% | 28.3% |
| NYT Connections (extended) | — | 30.1% |
| CritPt | 0% | — |
| Chess Puzzles | — | 4% |
| Mystery Game Puzzles | — | 5% |
| Surface Evolver Bench | 26.9% | — |
| Epoch Capabilities Index | — | 142.38 |
Math Qwen3 Max leads
Mistral Medium: 28.1 (#245), Qwen3 Max: 38.7 (#131)
| Benchmark | Mistral Medium | Qwen3 Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 32.2% | 73.3% |
| LMArena Math | 1408 | 1446 |
| MATH Level 5 | 81.6% | 97.1% |
| FrontierMath (Tiers 1-3) | — | 18.9% |
| ProofBench | 9% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Qwen3 Max leads
Mistral Medium: 25.0 (#265), Qwen3 Max: 48.1 (#78)
| Benchmark | Mistral Medium | Qwen3 Max |
|---|---|---|
| GPQA Diamond | 59.5% | 72.6% |
| LMArena Expert | 1408 | 1455 |
| Humanity's Last Exam | 4.5% | — |
| SimpleQA Verified | — | 48.7% |
| Vectara Hallucination Rate | 22.7% | — |
Multimodal Not comparable
Mistral Medium: 35.3 (#88), Qwen3 Max: —
| Benchmark | Mistral Medium | Qwen3 Max |
|---|---|---|
| LMArena Vision | 1172 | — |
Multilingual Qwen3 Max leads
Mistral Medium: 52.1 (#91), Qwen3 Max: 53.7 (#62)
| Benchmark | Mistral Medium | Qwen3 Max |
|---|---|---|
| LMArena Non-English | 1408 | 1429 |
| LMArena Chinese | 1447 | 1478 |
| LMArena French | 1459 | 1449 |
| LMArena German | 1432 | 1463 |
| LMArena Japanese | 1378 | 1397 |
| LMArena Korean | 1380 | 1399 |
| LMArena Russian | 1411 | 1428 |
| LMArena Spanish | 1433 | 1462 |
Instruction Following Qwen3 Max leads
Mistral Medium: 73.7 (#116), Qwen3 Max: 74.8 (#87)
| Benchmark | Mistral Medium | Qwen3 Max |
|---|---|---|
| LMArena Instruction Following | 1398 | 1419 |
Long Context Mistral Medium leads
Mistral Medium: 42.9 (#114), Qwen3 Max: 41.6 (#134)
| Benchmark | Mistral Medium | Qwen3 Max |
|---|---|---|
| LMArena Longer Query | 1406 | 1438 |
| Fiction.LiveBench | — | 66.7% |
| CL-bench | — | 14.5% |
Writing & Preference Qwen3 Max leads
Mistral Medium: 60.0 (#103), Qwen3 Max: 62.4 (#76)
| Benchmark | Mistral Medium | Qwen3 Max |
|---|---|---|
| LMArena Text | 1424 | 1439 |
| LMArena Creative Writing | 1391 | 1402 |
| LMArena Multi-Turn | 1418 | 1446 |
| Short-Story Creative Writing | 77.3% | — |
Frequently asked questions
Is Mistral Medium better than Qwen3 Max?
Qwen3 Max is the stronger model overall, scoring 43.7 to 36.3 on the Noometry Index.
Which is cheaper, Mistral Medium or Qwen3 Max?
Qwen3 Max is cheaper. It lists at $1.20 per million input tokens and $6 per million output tokens; Mistral Medium lists at $1.50 and $7.50.
Is Mistral Medium or Qwen3 Max better for coding?
Qwen3 Max scores higher on coding benchmarks: 43.0 versus 34.2 in the Noometry coding category.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Mistral Medium and Qwen3 Max share?
24 benchmarks have published results for both models. Mistral Medium has 36 scored results on Noometry and Qwen3 Max has 33.