Model comparison
Mistral Medium vs Qwen2.5-Max
Qwen2.5-Max is the stronger model overall, scoring 40.7 to 36.3 on the Noometry Index.
Last verified . 18 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Mistral Medium scores higher in 4 categories and Qwen2.5-Max in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen2.5-Max leads 35.3 to 25.0.
- Mistral Medium has downloadable open weights; the other is API-only.
Side by side
| Mistral Medium | Qwen2.5-Max | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 36.3 | 40.7 |
| Released | 2023-12-11 | 2025-01-25 |
| Weights | Open | Proprietary |
| Context window | 262K | — |
| Max output | 262K | — |
| Input $ / M tokens | $1.50 | — |
| Output $ / M tokens | $7.50 | — |
| Results tracked | 36 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5-Max leads
Mistral Medium: 34.2 (#243), Qwen2.5-Max: 41.8 (#117)
| Benchmark | Mistral Medium | Qwen2.5-Max |
|---|---|---|
| LMArena Coding | 1434 | 1359 |
| FrontierCode | 8% | — |
| SciCode | 40.2% | — |
| WeirdML | 43.7% | — |
| LiveBench Coding | — | 64.4% |
| ALE-Bench | 763.98 | — |
Agentic & Tool Use Not comparable
Mistral Medium: 28.3 (#90), Qwen2.5-Max: —
| Benchmark | Mistral Medium | Qwen2.5-Max |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.7% | — |
Reasoning Qwen2.5-Max leads
Mistral Medium: 24.0 (#167), Qwen2.5-Max: 25.6 (#147)
| Benchmark | Mistral Medium | Qwen2.5-Max |
|---|---|---|
| LMArena Hard Prompts | 1426 | 1360 |
| Kagi LLM Benchmark | 50% | — |
| CritPt | 0% | — |
| LiveBench Reasoning | — | 51.4% |
| DTBench | 75.5% | — |
| LiveBench Data Analysis | — | 67.9% |
| LMCA | 26.1% | — |
| Surface Evolver Bench | 26.9% | — |
| Epoch Capabilities Index | — | 132.53 |
| LiveBench | — | 62.3% |
Math Qwen2.5-Max leads
Mistral Medium: 28.1 (#245), Qwen2.5-Max: 36.9 (#162)
| Benchmark | Mistral Medium | Qwen2.5-Max |
|---|---|---|
| LMArena Math | 1408 | 1369 |
| OTIS Mock AIME 2024-2025 | 32.2% | — |
| ProofBench | 9% | — |
| LiveBench Math | — | 58.4% |
| MATH Level 5 | 81.6% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Qwen2.5-Max leads
Mistral Medium: 25.0 (#265), Qwen2.5-Max: 35.3 (#186)
| Benchmark | Mistral Medium | Qwen2.5-Max |
|---|---|---|
| LMArena Expert | 1408 | 1337 |
| GPQA Diamond | 59.5% | — |
| Humanity's Last Exam | 4.5% | — |
| Confabulations | — | 21.8% |
| Vectara Hallucination Rate | 22.7% | — |
Multimodal Not comparable
Mistral Medium: 35.3 (#88), Qwen2.5-Max: —
| Benchmark | Mistral Medium | Qwen2.5-Max |
|---|---|---|
| LMArena Vision | 1172 | — |
Multilingual Mistral Medium leads
Mistral Medium: 52.1 (#91), Qwen2.5-Max: 48.1 (#146)
| Benchmark | Mistral Medium | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | 1408 | 1352 |
| LMArena Chinese | 1447 | 1382 |
| LMArena French | 1459 | 1396 |
| LMArena German | 1432 | 1350 |
| LMArena Japanese | 1378 | 1300 |
| LMArena Korean | 1380 | 1304 |
| LMArena Russian | 1411 | 1353 |
| LMArena Spanish | 1433 | 1377 |
Instruction Following Mistral Medium leads
Mistral Medium: 73.7 (#116), Qwen2.5-Max: 71.3 (#152)
| Benchmark | Mistral Medium | Qwen2.5-Max |
|---|---|---|
| LMArena Instruction Following | 1398 | 1335 |
| LiveBench Instruction Following | — | 75.3% |
Long Context Mistral Medium leads
Mistral Medium: 42.9 (#114), Qwen2.5-Max: 41.4 (#142)
| Benchmark | Mistral Medium | Qwen2.5-Max |
|---|---|---|
| LMArena Longer Query | 1406 | 1358 |
Writing & Preference Mistral Medium leads
Mistral Medium: 60.0 (#103), Qwen2.5-Max: 55.4 (#146)
| Benchmark | Mistral Medium | Qwen2.5-Max |
|---|---|---|
| LMArena Text | 1424 | 1367 |
| LMArena Creative Writing | 1391 | 1339 |
| Short-Story Creative Writing | 77.3% | 72.9% |
| LMArena Multi-Turn | 1418 | 1364 |
| LiveBench Language | — | 56.3% |
Frequently asked questions
Is Mistral Medium better than Qwen2.5-Max?
Qwen2.5-Max is the stronger model overall, scoring 40.7 to 36.3 on the Noometry Index.
Is Mistral Medium or Qwen2.5-Max better for coding?
Qwen2.5-Max scores higher on coding benchmarks: 41.8 versus 34.2 in the Noometry coding category.
How many benchmarks do Mistral Medium and Qwen2.5-Max share?
18 benchmarks have published results for both models. Mistral Medium has 36 scored results on Noometry and Qwen2.5-Max has 27.