Model comparison
Mistral Large 3 vs Qwen2-72B
Mistral Large 3 is the stronger model overall, scoring 38.6 to 29.5 on the Noometry Index.
Last verified . 17 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Mistral Large 3 scores higher in 7 categories and Qwen2-72B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Large 3 leads 60.2 to 41.0.
Side by side
| Mistral Large 3 | Qwen2-72B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 38.6 | 29.5 |
| Released | 2025-12-02 | 2024-06-07 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $0.75 | — |
| Results tracked | 24 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Large 3 leads
Mistral Large 3: 34.1 (#230), Qwen2-72B: 28.7 (#303)
| Benchmark | Mistral Large 3 | Qwen2-72B |
|---|---|---|
| LMArena Coding | 1447 | 1196 |
| LMArena WebDev | 1230 | — |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |
Agentic & Tool Use Not comparable
Mistral Large 3: —, Qwen2-72B: 16.9 (#138)
| Benchmark | Mistral Large 3 | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
Reasoning Qwen2-72B leads
Mistral Large 3: 14.6 (#314), Qwen2-72B: 22.2 (#184)
| Benchmark | Mistral Large 3 | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1429 | 1191 |
| Kagi LLM Benchmark | 50.9% | — |
| NYT Connections (extended) | 7.5% | — |
| Thematic Generalization | 23% | — |
| Epoch Capabilities Index | — | 125.27 |
Math Mistral Large 3 leads
Mistral Large 3: 36.0 (#131), Qwen2-72B: 27.9 (#232)
| Benchmark | Mistral Large 3 | Qwen2-72B |
|---|---|---|
| LMArena Math | 1415 | 1235 |
| MATH Level 5 | — | 39.1% |
Knowledge Mistral Large 3 leads
Mistral Large 3: 35.5 (#173), Qwen2-72B: 21.2 (#270)
| Benchmark | Mistral Large 3 | Qwen2-72B |
|---|---|---|
| LMArena Expert | 1421 | 1171 |
| GPQA Diamond | — | 40.8% |
| Vectara Hallucination Rate | 14.5% | — |
| MMLU | — | 82.4% |
Multimodal Not comparable
Mistral Large 3: 37.6 (#65), Qwen2-72B: —
| Benchmark | Mistral Large 3 | Qwen2-72B |
|---|---|---|
| LMArena Vision | 1222 | — |
Multilingual Mistral Large 3 leads
Mistral Large 3: 52.6 (#79), Qwen2-72B: 36.0 (#239)
| Benchmark | Mistral Large 3 | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1412 | 1176 |
| LMArena Chinese | 1448 | 1240 |
| LMArena French | 1456 | 1169 |
| LMArena German | 1438 | 1151 |
| LMArena Japanese | 1399 | 1111 |
| LMArena Korean | 1384 | 1083 |
| LMArena Russian | 1412 | 1169 |
| LMArena Spanish | 1437 | 1168 |
Instruction Following Mistral Large 3 leads
Mistral Large 3: 74.1 (#104), Qwen2-72B: 62.0 (#236)
| Benchmark | Mistral Large 3 | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1402 | 1181 |
Long Context Mistral Large 3 leads
Mistral Large 3: 43.1 (#102), Qwen2-72B: 36.1 (#230)
| Benchmark | Mistral Large 3 | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1413 | 1193 |
Writing & Preference Mistral Large 3 leads
Mistral Large 3: 60.2 (#100), Qwen2-72B: 41.0 (#236)
| Benchmark | Mistral Large 3 | Qwen2-72B |
|---|---|---|
| LMArena Text | 1427 | 1203 |
| LMArena Creative Writing | 1385 | 1181 |
| LMArena Multi-Turn | 1429 | 1195 |
| EQ-Bench Creative Writing | 1412 | — |
Frequently asked questions
Is Mistral Large 3 better than Qwen2-72B?
Mistral Large 3 is the stronger model overall, scoring 38.6 to 29.5 on the Noometry Index.
Is Mistral Large 3 or Qwen2-72B better for coding?
Mistral Large 3 scores higher on coding benchmarks: 34.1 versus 28.7 in the Noometry coding category.
How many benchmarks do Mistral Large 3 and Qwen2-72B share?
17 benchmarks have published results for both models. Mistral Large 3 has 24 scored results on Noometry and Qwen2-72B has 26.