Model comparison
Mistral Medium 3.5 vs Qwen2-72B
Mistral Medium 3.5 is the stronger model overall, scoring 40.2 to 30.0 on the Noometry Index.
Last verified . 17 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Mistral Medium 3.5 scores higher in 7 categories and Qwen2-72B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mistral Medium 3.5 leads 40.0 to 21.2.
Side by side
| Mistral Medium 3.5 | Qwen2-72B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 40.2 | 30.0 |
| Released | — | 2024-06-07 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 210K | — |
| Input $ / M tokens | $1.50 | — |
| Output $ / M tokens | $7.50 | — |
| Results tracked | 22 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Medium 3.5 leads
Mistral Medium 3.5: 36.0 (#213), Qwen2-72B: 29.1 (#310)
| Benchmark | Mistral Medium 3.5 | Qwen2-72B |
|---|---|---|
| LMArena Coding | 1461 | 1196 |
| LMArena WebDev | 1264 | — |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |
Agentic & Tool Use Not comparable
Mistral Medium 3.5: —, Qwen2-72B: 17.0 (#146)
| Benchmark | Mistral Medium 3.5 | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
Reasoning Qwen2-72B leads
Mistral Medium 3.5: 17.3 (#295), Qwen2-72B: 23.2 (#181)
| Benchmark | Mistral Medium 3.5 | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1436 | 1191 |
| Epoch Capabilities Index | 141.35 | 125.28 |
| Kagi LLM Benchmark | 41.4% | — |
| NYT Connections (extended) | 12.9% | — |
Math Mistral Medium 3.5 leads
Mistral Medium 3.5: 39.1 (#113), Qwen2-72B: 30.2 (#236)
| Benchmark | Mistral Medium 3.5 | Qwen2-72B |
|---|---|---|
| LMArena Math | 1431 | 1235 |
| MATH Level 5 | — | 39.1% |
Knowledge Mistral Medium 3.5 leads
Mistral Medium 3.5: 40.0 (#126), Qwen2-72B: 21.2 (#275)
| Benchmark | Mistral Medium 3.5 | Qwen2-72B |
|---|---|---|
| LMArena Expert | 1432 | 1171 |
| GPQA Diamond | — | 40.8% |
| MMLU | — | 82.4% |
Multimodal Not comparable
Mistral Medium 3.5: 38.3 (#65), Qwen2-72B: —
| Benchmark | Mistral Medium 3.5 | Qwen2-72B |
|---|---|---|
| LMArena Vision | 1223 | — |
Multilingual Mistral Medium 3.5 leads
Mistral Medium 3.5: 51.9 (#100), Qwen2-72B: 35.9 (#244)
| Benchmark | Mistral Medium 3.5 | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1404 | 1176 |
| LMArena Chinese | 1442 | 1240 |
| LMArena French | 1448 | 1170 |
| LMArena German | 1451 | 1151 |
| LMArena Korean | 1385 | 1083 |
| LMArena Russian | 1395 | 1169 |
| LMArena Spanish | 1409 | 1169 |
| LMArena Japanese | — | 1111 |
Instruction Following Mistral Medium 3.5 leads
Mistral Medium 3.5: 74.6 (#90), Qwen2-72B: 61.7 (#241)
| Benchmark | Mistral Medium 3.5 | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1415 | 1181 |
Long Context Mistral Medium 3.5 leads
Mistral Medium 3.5: 43.2 (#103), Qwen2-72B: 36.1 (#235)
| Benchmark | Mistral Medium 3.5 | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1415 | 1192 |
Writing & Preference Mistral Medium 3.5 leads
Mistral Medium 3.5: 58.5 (#117), Qwen2-72B: 40.8 (#241)
| Benchmark | Mistral Medium 3.5 | Qwen2-72B |
|---|---|---|
| LMArena Text | 1421 | 1203 |
| LMArena Creative Writing | 1374 | 1181 |
| LMArena Multi-Turn | 1423 | 1196 |
| EQ-Bench 4 | 993 | — |
Frequently asked questions
Is Mistral Medium 3.5 better than Qwen2-72B?
Mistral Medium 3.5 is the stronger model overall, scoring 40.2 to 30.0 on the Noometry Index.
Is Mistral Medium 3.5 or Qwen2-72B better for coding?
Mistral Medium 3.5 scores higher on coding benchmarks: 36.0 versus 29.1 in the Noometry coding category.
How many benchmarks do Mistral Medium 3.5 and Qwen2-72B share?
17 benchmarks have published results for both models. Mistral Medium 3.5 has 22 scored results on Noometry and Qwen2-72B has 26.