Model comparison
Mistral vs Qwen2.5-Coder-32B
Qwen2.5-Coder-32B is the stronger model overall, scoring 33.4 to 29.9 on the Noometry Index.
Last verified . 12 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. Mistral scores higher in 2 categories and Qwen2.5-Coder-32B in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen2.5-Coder-32B leads 33.4 to 16.6.
- Qwen2.5-Coder-32B has downloadable open weights; the other is API-only.
Side by side
| Mistral | Qwen2.5-Coder-32B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 29.9 | 33.4 |
| Released | — | 2024-09-18 |
| Weights | Proprietary | Open |
| Context window | — | 33K |
| Max output | — | 29K |
| Input $ / M tokens | — | $0.66 |
| Output $ / M tokens | — | $1 |
| Results tracked | 22 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral leads
Mistral: 33.8 (#250), Qwen2.5-Coder-32B: 22.6 (#333)
| Benchmark | Mistral | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Coding | 1162 | 1276 |
| SWE-bench Verified (bash only) | — | 9% |
| Aider Polyglot | — | 16.4% |
| BigCodeBench Instruct | — | 49% |
| LiveBench Coding | — | 56.9% |
| BigCodeBench Complete | — | 58% |
| HumanEval+ | — | 87.2% |
| MBPP+ | — | 77% |
Reasoning Mistral leads
Mistral: 22.2 (#200), Qwen2.5-Coder-32B: 21.2 (#225)
| Benchmark | Mistral | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Hard Prompts | 1149 | 1251 |
| LiveBench Reasoning | — | 42.1% |
| LiveBench Data Analysis | — | 49.9% |
| Epoch Capabilities Index | — | 119.49 |
| HellaSwag | — | 83% |
| LiveBench | — | 46.2% |
| WinoGrande | — | 80.8% |
Math Qwen2.5-Coder-32B leads
Mistral: 22.3 (#278), Qwen2.5-Coder-32B: 33.3 (#204)
| Benchmark | Mistral | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Math | 1180 | 1251 |
| Omni-MATH | 7.2% | — |
| LiveBench Math | — | 46.6% |
| GSM8K | — | 93% |
Knowledge Qwen2.5-Coder-32B leads
Mistral: 16.6 (#288), Qwen2.5-Coder-32B: 33.4 (#203)
| Benchmark | Mistral | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Expert | 1125 | 1221 |
| MMLU-Pro | 27.7% | — |
| GPQA (HELM) | 30.3% | — |
| ARC (AI2) Challenge | — | 70.5% |
| MMLU | — | 79.1% |
Multilingual Qwen2.5-Coder-32B leads
Mistral: 32.8 (#254), Qwen2.5-Coder-32B: 37.8 (#235)
| Benchmark | Mistral | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Non-English | 1129 | 1205 |
| LMArena Chinese | 1109 | 1222 |
| LMArena Russian | 1168 | 1228 |
| LMArena French | 1180 | — |
| LMArena German | 1155 | — |
| LMArena Japanese | 1013 | — |
| LMArena Korean | 1032 | — |
| LMArena Spanish | 1143 | — |
Instruction Following Qwen2.5-Coder-32B leads
Mistral: 52.6 (#288), Qwen2.5-Coder-32B: 61.4 (#245)
| Benchmark | Mistral | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Instruction Following | 1152 | 1223 |
| LiveBench Instruction Following | — | 58.7% |
| IFEval | 56.8% | — |
Long Context Qwen2.5-Coder-32B leads
Mistral: 35.0 (#245), Qwen2.5-Coder-32B: 38.0 (#208)
| Benchmark | Mistral | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Longer Query | 1153 | 1251 |
Writing & Preference Qwen2.5-Coder-32B leads
Mistral: 37.0 (#260), Qwen2.5-Coder-32B: 41.6 (#240)
| Benchmark | Mistral | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Text | 1165 | 1230 |
| LMArena Creative Writing | 1158 | 1174 |
| LMArena Multi-Turn | 1147 | 1222 |
| WildBench | 66% | — |
| LiveBench Language | — | 23.3% |
Frequently asked questions
Is Mistral better than Qwen2.5-Coder-32B?
Qwen2.5-Coder-32B is the stronger model overall, scoring 33.4 to 29.9 on the Noometry Index.
Is Mistral or Qwen2.5-Coder-32B better for coding?
Mistral scores higher on coding benchmarks: 33.8 versus 22.6 in the Noometry coding category.
How many benchmarks do Mistral and Qwen2.5-Coder-32B share?
12 benchmarks have published results for both models. Mistral has 22 scored results on Noometry and Qwen2.5-Coder-32B has 31.