Model comparison
Mistral vs Qwen2-72B
Mistral and Qwen2-72B score almost the same on the Noometry Index (29.9 vs 30.0), so choose on price, context window or the category you care about most.
Last verified . 17 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Mistral scores higher in 1 category and Qwen2-72B in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Qwen2-72B leads 61.7 to 52.6.
- Qwen2-72B has downloadable open weights; the other is API-only.
Side by side
| Mistral | Qwen2-72B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 29.9 | 30.0 |
| Released | — | 2024-06-07 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 22 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral leads
Mistral: 33.8 (#250), Qwen2-72B: 29.1 (#310)
| Benchmark | Mistral | Qwen2-72B |
|---|---|---|
| LMArena Coding | 1162 | 1196 |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |
Agentic & Tool Use Not comparable
Mistral: —, Qwen2-72B: 17.0 (#146)
| Benchmark | Mistral | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
Reasoning Too close to call
Mistral: 22.2 (#200), Qwen2-72B: 23.2 (#181)
| Benchmark | Mistral | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1149 | 1191 |
| Epoch Capabilities Index | — | 125.28 |
Math Qwen2-72B leads
Mistral: 22.3 (#278), Qwen2-72B: 30.2 (#236)
| Benchmark | Mistral | Qwen2-72B |
|---|---|---|
| LMArena Math | 1180 | 1235 |
| Omni-MATH | 7.2% | — |
| MATH Level 5 | — | 39.1% |
Knowledge Qwen2-72B leads
Mistral: 16.6 (#288), Qwen2-72B: 21.2 (#275)
| Benchmark | Mistral | Qwen2-72B |
|---|---|---|
| LMArena Expert | 1125 | 1171 |
| GPQA Diamond | — | 40.8% |
| MMLU-Pro | 27.7% | — |
| GPQA (HELM) | 30.3% | — |
| MMLU | — | 82.4% |
Multilingual Qwen2-72B leads
Mistral: 32.8 (#254), Qwen2-72B: 35.9 (#244)
| Benchmark | Mistral | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1129 | 1176 |
| LMArena Chinese | 1109 | 1240 |
| LMArena French | 1180 | 1170 |
| LMArena German | 1155 | 1151 |
| LMArena Japanese | 1013 | 1111 |
| LMArena Korean | 1032 | 1083 |
| LMArena Russian | 1168 | 1169 |
| LMArena Spanish | 1143 | 1169 |
Instruction Following Qwen2-72B leads
Mistral: 52.6 (#288), Qwen2-72B: 61.7 (#241)
| Benchmark | Mistral | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1152 | 1181 |
| IFEval | 56.8% | — |
Long Context Qwen2-72B leads
Mistral: 35.0 (#245), Qwen2-72B: 36.1 (#235)
| Benchmark | Mistral | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1153 | 1192 |
Writing & Preference Qwen2-72B leads
Mistral: 37.0 (#260), Qwen2-72B: 40.8 (#241)
| Benchmark | Mistral | Qwen2-72B |
|---|---|---|
| LMArena Text | 1165 | 1203 |
| LMArena Creative Writing | 1158 | 1181 |
| LMArena Multi-Turn | 1147 | 1196 |
| WildBench | 66% | — |
Frequently asked questions
Is Mistral better than Qwen2-72B?
Mistral and Qwen2-72B score almost the same on the Noometry Index (29.9 vs 30.0), so choose on price, context window or the category you care about most.
Is Mistral or Qwen2-72B better for coding?
Mistral scores higher on coding benchmarks: 33.8 versus 29.1 in the Noometry coding category.
How many benchmarks do Mistral and Qwen2-72B share?
17 benchmarks have published results for both models. Mistral has 22 scored results on Noometry and Qwen2-72B has 26.