Model comparison
Mistral Medium vs Qwen3.6 Max Preview
Qwen3.6 Max Preview is the stronger model overall, scoring 51.1 to 36.0 on the Noometry Index.
Last verified . 19 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 19 benchmarks with published results for both. Mistral Medium scores higher in 0 categories and Qwen3.6 Max Preview in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.6 Max Preview leads 57.6 to 24.9.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 32.2% for Mistral Medium and 91.1% for Qwen3.6 Max Preview.
- Both cost about the same: $1.50 input and $7.50 output per million tokens.
- Mistral Medium has downloadable open weights; the other is API-only.
Side by side
| Mistral Medium | Qwen3.6 Max Preview | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 36.0 | 51.1 |
| Released | 2023-12-11 | 2026-04-20 |
| Weights | Open | Proprietary |
| Context window | 262K | 262K |
| Max output | 262K | 66K |
| Input $ / M tokens | $1.50 | $1.30 |
| Output $ / M tokens | $7.50 | $7.80 |
| Results tracked | 36 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.6 Max Preview leads
Mistral Medium: 33.8 (#241), Qwen3.6 Max Preview: 48.6 (#50)
| Benchmark | Mistral Medium | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Coding | 1434 | 1472 |
| SWE-bench Verified | — | 76.7% |
| FrontierCode | 8% | — |
| LMArena WebDev | — | 1482 |
| SciCode | 40.2% | — |
| WeirdML | 43.7% | — |
| ALE-Bench | 763.98 | — |
Agentic & Tool Use Not comparable
Mistral Medium: 28.1 (#84), Qwen3.6 Max Preview: —
| Benchmark | Mistral Medium | Qwen3.6 Max Preview |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.7% | — |
| Vending-Bench 2 | — | 4,254 |
Reasoning Qwen3.6 Max Preview leads
Mistral Medium: 23.3 (#165), Qwen3.6 Max Preview: 40.8 (#47)
| Benchmark | Mistral Medium | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Hard Prompts | 1426 | 1457 |
| DTBench | 75.5% | 87.2% |
| LMCA | 26.1% | 42.5% |
| SimpleBench | — | 63% |
| Kagi LLM Benchmark | 50% | — |
| NYT Connections (extended) | — | 74.1% |
| CritPt | 0% | — |
| Chess Puzzles | — | 20% |
| Mystery Game Puzzles | — | 19% |
| Surface Evolver Bench | 26.9% | — |
| Epoch Capabilities Index | — | 149.27 |
Math Qwen3.6 Max Preview leads
Mistral Medium: 27.2 (#238), Qwen3.6 Max Preview: 52.2 (#40)
| Benchmark | Mistral Medium | Qwen3.6 Max Preview |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 32.2% | 91.1% |
| LMArena Math | 1409 | 1465 |
| FrontierMath (Feb 2025 set) | 0.3% | 23.1% |
| ProofBench | 9% | — |
| MATH Level 5 | 81.6% | — |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Qwen3.6 Max Preview leads
Mistral Medium: 24.9 (#260), Qwen3.6 Max Preview: 57.6 (#35)
| Benchmark | Mistral Medium | Qwen3.6 Max Preview |
|---|---|---|
| GPQA Diamond | 59.5% | 87.4% |
| LMArena Expert | 1408 | 1476 |
| Humanity's Last Exam | 4.5% | — |
| SimpleQA Verified | — | 52% |
| Vectara Hallucination Rate | 22.7% | — |
Multimodal Not comparable
Mistral Medium: 34.6 (#82), Qwen3.6 Max Preview: —
| Benchmark | Mistral Medium | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Vision | 1172 | — |
Multilingual Qwen3.6 Max Preview leads
Mistral Medium: 52.3 (#86), Qwen3.6 Max Preview: 54.3 (#46)
| Benchmark | Mistral Medium | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Non-English | 1408 | 1436 |
| LMArena Chinese | 1448 | 1487 |
| LMArena French | 1460 | 1449 |
| LMArena Russian | 1411 | 1444 |
| LMArena Spanish | 1433 | 1452 |
| LMArena German | 1433 | — |
| LMArena Japanese | 1378 | — |
| LMArena Korean | 1382 | — |
Instruction Following Qwen3.6 Max Preview leads
Mistral Medium: 73.9 (#111), Qwen3.6 Max Preview: 75.8 (#51)
| Benchmark | Mistral Medium | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Instruction Following | 1398 | 1437 |
Long Context Qwen3.6 Max Preview leads
Mistral Medium: 42.9 (#108), Qwen3.6 Max Preview: 44.6 (#59)
| Benchmark | Mistral Medium | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Longer Query | 1406 | 1457 |
Writing & Preference Qwen3.6 Max Preview leads
Mistral Medium: 60.2 (#97), Qwen3.6 Max Preview: 64.0 (#58)
| Benchmark | Mistral Medium | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Text | 1424 | 1447 |
| LMArena Creative Writing | 1391 | 1435 |
| LMArena Multi-Turn | 1418 | 1456 |
| Short-Story Creative Writing | 77.3% | — |
Frequently asked questions
Is Mistral Medium better than Qwen3.6 Max Preview?
Qwen3.6 Max Preview is the stronger model overall, scoring 51.1 to 36.0 on the Noometry Index.
Which is cheaper, Mistral Medium or Qwen3.6 Max Preview?
Qwen3.6 Max Preview is cheaper. It lists at $1.30 per million input tokens and $7.80 per million output tokens; Mistral Medium lists at $1.50 and $7.50.
Is Mistral Medium or Qwen3.6 Max Preview better for coding?
Qwen3.6 Max Preview scores higher on coding benchmarks: 48.6 versus 33.8 in the Noometry coding category.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Mistral Medium and Qwen3.6 Max Preview share?
19 benchmarks have published results for both models. Mistral Medium has 36 scored results on Noometry and Qwen3.6 Max Preview has 29.