Model comparison
Mistral Large vs Qwen1.5-32B
Mistral Large is the stronger model overall, scoring 31.9 to 30.5 on the Noometry Index.
Last verified . 21 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 21 benchmarks with published results for both. Mistral Large scores higher in 6 categories and Qwen1.5-32B in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mistral Large leads 30.1 to 13.5.
- The biggest single-benchmark swing is GPQA Diamond: 51.3% for Mistral Large and 30.7% for Qwen1.5-32B.
Side by side
| Mistral Large | Qwen1.5-32B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 31.9 | 30.5 |
| Released | 2024-02-26 | 2024-02-04 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 16K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $6 | — |
| Results tracked | 51 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Large leads
Mistral Large: 34.3 (#240), Qwen1.5-32B: 31.7 (#282)
| Benchmark | Mistral Large | Qwen1.5-32B |
|---|---|---|
| BigCodeBench Instruct | 30% | 32.3% |
| LMArena Coding | 1277 | 1155 |
| BigCodeBench Complete | 38.3% | 42% |
| SciCode | 36.2% | — |
| LiveBench Coding | 47.1% | — |
| ALE-Bench | 264.7 | — |
| HumanEval+ | 62.2% | — |
| MBPP+ | 59.5% | — |
Agentic & Tool Use Not comparable
Mistral Large: 28.6 (#89), Qwen1.5-32B: —
| Benchmark | Mistral Large | Qwen1.5-32B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 38.4% | — |
Reasoning Qwen1.5-32B leads
Mistral Large: 15.8 (#310), Qwen1.5-32B: 21.8 (#212)
| Benchmark | Mistral Large | Qwen1.5-32B |
|---|---|---|
| LMArena Hard Prompts | 1257 | 1130 |
| SimpleBench | 22.5% | — |
| CritPt | 0% | — |
| LiveBench Reasoning | 43.5% | — |
| DTBench | 65.1% | — |
| LiveBench Data Analysis | 50.1% | — |
| LMCA | 16.7% | — |
| Epoch Capabilities Index | 128.52 | — |
| ForecastBench | 57.1 | — |
| LiveBench | 48.4% | — |
Math Qwen1.5-32B leads
Mistral Large: 18.2 (#291), Qwen1.5-32B: 33.0 (#207)
| Benchmark | Mistral Large | Qwen1.5-32B |
|---|---|---|
| LMArena Math | 1262 | 1155 |
| OTIS Mock AIME 2024-2025 | 8.5% | — |
| Omni-MATH | 28.1% | — |
| LiveBench Math | 42.5% | — |
| MATH Level 5 | 50.3% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Mistral Large leads
Mistral Large: 30.1 (#230), Qwen1.5-32B: 13.5 (#296)
| Benchmark | Mistral Large | Qwen1.5-32B |
|---|---|---|
| GPQA Diamond | 51.3% | 30.7% |
| LMArena Expert | 1232 | 1126 |
| MMLU | 80% | 74.4% |
| MMLU-Pro | 59.9% | — |
| Confabulations | 21.4% | — |
| Vectara Hallucination Rate | 4.5% | — |
| GPQA (HELM) | 43.5% | — |
Multilingual Mistral Large leads
Mistral Large: 40.0 (#219), Qwen1.5-32B: 31.4 (#259)
| Benchmark | Mistral Large | Qwen1.5-32B |
|---|---|---|
| LMArena Non-English | 1237 | 1106 |
| LMArena Chinese | 1240 | 1177 |
| LMArena French | 1325 | 1101 |
| LMArena German | 1254 | 1058 |
| LMArena Japanese | 1188 | 1027 |
| LMArena Korean | 1202 | 1008 |
| LMArena Russian | 1257 | 1073 |
| LMArena Spanish | 1268 | 1089 |
Instruction Following Mistral Large leads
Mistral Large: 67.9 (#191), Qwen1.5-32B: 57.7 (#265)
| Benchmark | Mistral Large | Qwen1.5-32B |
|---|---|---|
| LMArena Instruction Following | 1249 | 1116 |
| LiveBench Instruction Following | 67.9% | — |
| IFEval | 87.7% | — |
Long Context Mistral Large leads
Mistral Large: 38.3 (#199), Qwen1.5-32B: 34.7 (#246)
| Benchmark | Mistral Large | Qwen1.5-32B |
|---|---|---|
| LMArena Longer Query | 1261 | 1146 |
Writing & Preference Mistral Large leads
Mistral Large: 40.7 (#242), Qwen1.5-32B: 34.2 (#271)
| Benchmark | Mistral Large | Qwen1.5-32B |
|---|---|---|
| LMArena Text | 1266 | 1137 |
| LMArena Creative Writing | 1243 | 1083 |
| LMArena Multi-Turn | 1260 | 1140 |
| Short-Story Creative Writing | 69% | — |
| EQ-Bench Creative Writing | 985 | — |
| WildBench | 80.1% | — |
| LiveBench Language | 39.4% | — |
Frequently asked questions
Is Mistral Large better than Qwen1.5-32B?
Mistral Large is the stronger model overall, scoring 31.9 to 30.5 on the Noometry Index.
Is Mistral Large or Qwen1.5-32B better for coding?
Mistral Large scores higher on coding benchmarks: 34.3 versus 31.7 in the Noometry coding category.
How many benchmarks do Mistral Large and Qwen1.5-32B share?
21 benchmarks have published results for both models. Mistral Large has 51 scored results on Noometry and Qwen1.5-32B has 21.