Model comparison
Mistral Large 4 vs Qwen2-72B
Mistral Large 4 is the stronger model overall, scoring 43.1 to 30.0 on the Noometry Index.
Last verified . 12 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. Mistral Large 4 scores higher in 7 categories and Qwen2-72B in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Large 4 leads 60.4 to 40.8.
- Qwen2-72B has downloadable open weights; the other is API-only.
Side by side
| Mistral Large 4 | Qwen2-72B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 43.1 | 30.0 |
| Released | 2026-10-06 | 2024-06-07 |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 262K | — |
| Input $ / M tokens | $0.68 | — |
| Output $ / M tokens | $2.09 | — |
| Results tracked | 15 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Large 4 leads
Mistral Large 4: 48.6 (#57), Qwen2-72B: 29.1 (#310)
| Benchmark | Mistral Large 4 | Qwen2-72B |
|---|---|---|
| LMArena Coding | 1475 | 1196 |
| LMArena WebDev | 1541 | — |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |
Agentic & Tool Use Not comparable
Mistral Large 4: —, Qwen2-72B: 17.0 (#146)
| Benchmark | Mistral Large 4 | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
Reasoning Too close to call
Mistral Large 4: 22.5 (#192), Qwen2-72B: 23.2 (#181)
| Benchmark | Mistral Large 4 | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1444 | 1191 |
| NYT Connections (extended) | 27.4% | — |
| Epoch Capabilities Index | — | 125.28 |
Math Mistral Large 4 leads
Mistral Large 4: 40.4 (#91), Qwen2-72B: 30.2 (#236)
| Benchmark | Mistral Large 4 | Qwen2-72B |
|---|---|---|
| LMArena Math | 1488 | 1235 |
| MATH Level 5 | — | 39.1% |
Knowledge Mistral Large 4 leads
Mistral Large 4: 36.6 (#166), Qwen2-72B: 21.2 (#275)
| Benchmark | Mistral Large 4 | Qwen2-72B |
|---|---|---|
| LMArena Expert | 1447 | 1171 |
| GPQA Diamond | — | 40.8% |
| SimpleQA Verified | 20% | — |
| MMLU | — | 82.4% |
Multilingual Mistral Large 4 leads
Mistral Large 4: 52.6 (#82), Qwen2-72B: 35.9 (#244)
| Benchmark | Mistral Large 4 | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1415 | 1176 |
| LMArena Chinese | 1491 | 1240 |
| LMArena Russian | 1414 | 1169 |
| LMArena French | — | 1170 |
| LMArena German | — | 1151 |
| LMArena Japanese | — | 1111 |
| LMArena Korean | — | 1083 |
| LMArena Spanish | — | 1169 |
Instruction Following Mistral Large 4 leads
Mistral Large 4: 75.0 (#76), Qwen2-72B: 61.7 (#241)
| Benchmark | Mistral Large 4 | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1424 | 1181 |
Long Context Mistral Large 4 leads
Mistral Large 4: 43.6 (#89), Qwen2-72B: 36.1 (#235)
| Benchmark | Mistral Large 4 | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1429 | 1192 |
Writing & Preference Mistral Large 4 leads
Mistral Large 4: 60.4 (#97), Qwen2-72B: 40.8 (#241)
| Benchmark | Mistral Large 4 | Qwen2-72B |
|---|---|---|
| LMArena Text | 1427 | 1203 |
| LMArena Creative Writing | 1361 | 1181 |
| LMArena Multi-Turn | 1424 | 1196 |
Frequently asked questions
Is Mistral Large 4 better than Qwen2-72B?
Mistral Large 4 is the stronger model overall, scoring 43.1 to 30.0 on the Noometry Index.
Is Mistral Large 4 or Qwen2-72B better for coding?
Mistral Large 4 scores higher on coding benchmarks: 48.6 versus 29.1 in the Noometry coding category.
How many benchmarks do Mistral Large 4 and Qwen2-72B share?
12 benchmarks have published results for both models. Mistral Large 4 has 15 scored results on Noometry and Qwen2-72B has 26.