Model comparison
Mistral Medium vs Qwen2-72B
Mistral Medium is the stronger model overall, scoring 36.3 to 30.0 on the Noometry Index.
Last verified . 20 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 20 benchmarks with published results for both. Mistral Medium scores higher in 8 categories and Qwen2-72B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Medium leads 60.0 to 40.8.
- The biggest single-benchmark swing is MATH Level 5: 81.6% for Mistral Medium and 39.1% for Qwen2-72B.
Side by side
| Mistral Medium | Qwen2-72B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 36.3 | 30.0 |
| Released | 2023-12-11 | 2024-06-07 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 262K | — |
| Input $ / M tokens | $1.50 | — |
| Output $ / M tokens | $7.50 | — |
| Results tracked | 36 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Medium leads
Mistral Medium: 34.2 (#243), Qwen2-72B: 29.1 (#310)
| Benchmark | Mistral Medium | Qwen2-72B |
|---|---|---|
| WeirdML | 43.7% | 11.3% |
| LMArena Coding | 1434 | 1196 |
| FrontierCode | 8% | — |
| SciCode | 40.2% | — |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |
| ALE-Bench | 763.98 | — |
Agentic & Tool Use Mistral Medium leads
Mistral Medium: 28.3 (#90), Qwen2-72B: 17.0 (#146)
| Benchmark | Mistral Medium | Qwen2-72B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.7% | — |
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
Reasoning Too close to call
Mistral Medium: 24.0 (#167), Qwen2-72B: 23.2 (#181)
| Benchmark | Mistral Medium | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1426 | 1191 |
| Kagi LLM Benchmark | 50% | — |
| CritPt | 0% | — |
| DTBench | 75.5% | — |
| LMCA | 26.1% | — |
| Surface Evolver Bench | 26.9% | — |
| Epoch Capabilities Index | — | 125.28 |
Math Qwen2-72B leads
Mistral Medium: 28.1 (#245), Qwen2-72B: 30.2 (#236)
| Benchmark | Mistral Medium | Qwen2-72B |
|---|---|---|
| LMArena Math | 1408 | 1235 |
| MATH Level 5 | 81.6% | 39.1% |
| OTIS Mock AIME 2024-2025 | 32.2% | — |
| ProofBench | 9% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Mistral Medium leads
Mistral Medium: 25.0 (#265), Qwen2-72B: 21.2 (#275)
| Benchmark | Mistral Medium | Qwen2-72B |
|---|---|---|
| GPQA Diamond | 59.5% | 40.8% |
| LMArena Expert | 1408 | 1171 |
| Humanity's Last Exam | 4.5% | — |
| Vectara Hallucination Rate | 22.7% | — |
| MMLU | — | 82.4% |
Multimodal Not comparable
Mistral Medium: 35.3 (#88), Qwen2-72B: —
| Benchmark | Mistral Medium | Qwen2-72B |
|---|---|---|
| LMArena Vision | 1172 | — |
Multilingual Mistral Medium leads
Mistral Medium: 52.1 (#91), Qwen2-72B: 35.9 (#244)
| Benchmark | Mistral Medium | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1408 | 1176 |
| LMArena Chinese | 1447 | 1240 |
| LMArena French | 1459 | 1170 |
| LMArena German | 1432 | 1151 |
| LMArena Japanese | 1378 | 1111 |
| LMArena Korean | 1380 | 1083 |
| LMArena Russian | 1411 | 1169 |
| LMArena Spanish | 1433 | 1169 |
Instruction Following Mistral Medium leads
Mistral Medium: 73.7 (#116), Qwen2-72B: 61.7 (#241)
| Benchmark | Mistral Medium | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1398 | 1181 |
Long Context Mistral Medium leads
Mistral Medium: 42.9 (#114), Qwen2-72B: 36.1 (#235)
| Benchmark | Mistral Medium | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1406 | 1192 |
Writing & Preference Mistral Medium leads
Mistral Medium: 60.0 (#103), Qwen2-72B: 40.8 (#241)
| Benchmark | Mistral Medium | Qwen2-72B |
|---|---|---|
| LMArena Text | 1424 | 1203 |
| LMArena Creative Writing | 1391 | 1181 |
| LMArena Multi-Turn | 1418 | 1196 |
| Short-Story Creative Writing | 77.3% | — |
Frequently asked questions
Is Mistral Medium better than Qwen2-72B?
Mistral Medium is the stronger model overall, scoring 36.3 to 30.0 on the Noometry Index.
Is Mistral Medium or Qwen2-72B better for coding?
Mistral Medium scores higher on coding benchmarks: 34.2 versus 29.1 in the Noometry coding category.
How many benchmarks do Mistral Medium and Qwen2-72B share?
20 benchmarks have published results for both models. Mistral Medium has 36 scored results on Noometry and Qwen2-72B has 26.