Model comparison
Mistral 7B vs Qwen1.5-32B
Qwen1.5-32B is the stronger model overall, scoring 30.5 to 23.0 on the Noometry Index.
Last verified . 20 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 20 benchmarks with published results for both. Mistral 7B scores higher in 0 categories and Qwen1.5-32B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen1.5-32B leads 33.0 to 8.1.
- The biggest single-benchmark swing is GPQA Diamond: 15.2% for Mistral 7B and 30.7% for Qwen1.5-32B.
Side by side
| Mistral 7B | Qwen1.5-32B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 23.0 | 30.5 |
| Released | 2023-09-27 | 2024-02-04 |
| Weights | Open | Open |
| Context window | 8K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $0.25 | — |
| Results tracked | 37 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen1.5-32B leads
Mistral 7B: 26.4 (#326), Qwen1.5-32B: 31.7 (#282)
| Benchmark | Mistral 7B | Qwen1.5-32B |
|---|---|---|
| BigCodeBench Instruct | 19.5% | 32.3% |
| LMArena Coding | 1082 | 1155 |
| BigCodeBench Complete | 27.3% | 42% |
| HumanEval+ | 36% | — |
| MBPP+ | 42.1% | — |
Reasoning Qwen1.5-32B leads
Mistral 7B: 13.1 (#336), Qwen1.5-32B: 21.8 (#212)
| Benchmark | Mistral 7B | Qwen1.5-32B |
|---|---|---|
| LMArena Hard Prompts | 1067 | 1130 |
| Chess Puzzles | 0% | — |
| DTBench | 42.5% | — |
| Adversarial NLI | 47.1% | — |
| BIG-Bench Hard | 56.1% | — |
| Epoch Capabilities Index | 112.21 | — |
| HellaSwag | 81% | — |
| PIQA | 83% | — |
| WinoGrande | 75.3% | — |
Math Qwen1.5-32B leads
Mistral 7B: 8.1 (#325), Qwen1.5-32B: 33.0 (#207)
| Benchmark | Mistral 7B | Qwen1.5-32B |
|---|---|---|
| LMArena Math | 1085 | 1155 |
| OTIS Mock AIME 2024-2025 | 0.3% | — |
| MATH Level 5 | 3.7% | — |
| GSM8K | 54.4% | — |
Knowledge Qwen1.5-32B leads
Mistral 7B: 7.4 (#311), Qwen1.5-32B: 13.5 (#296)
| Benchmark | Mistral 7B | Qwen1.5-32B |
|---|---|---|
| GPQA Diamond | 15.2% | 30.7% |
| LMArena Expert | 1036 | 1126 |
| MMLU | 62.5% | 74.4% |
| ARC (AI2) Challenge | 78.6% | — |
| BoolQ | 87.4% | — |
| OpenBookQA | 79.8% | — |
| TriviaQA | 75.2% | — |
Multilingual Qwen1.5-32B leads
Mistral 7B: 25.8 (#283), Qwen1.5-32B: 31.4 (#259)
| Benchmark | Mistral 7B | Qwen1.5-32B |
|---|---|---|
| LMArena Non-English | 1012 | 1106 |
| LMArena Chinese | 1009 | 1177 |
| LMArena French | 1037 | 1101 |
| LMArena German | 987 | 1058 |
| LMArena Japanese | 878 | 1027 |
| LMArena Russian | 1018 | 1073 |
| LMArena Spanish | 1026 | 1089 |
| LMArena Korean | — | 1008 |
Instruction Following Qwen1.5-32B leads
Mistral 7B: 54.2 (#280), Qwen1.5-32B: 57.7 (#265)
| Benchmark | Mistral 7B | Qwen1.5-32B |
|---|---|---|
| LMArena Instruction Following | 1060 | 1116 |
Long Context Qwen1.5-32B leads
Mistral 7B: 32.2 (#271), Qwen1.5-32B: 34.7 (#246)
| Benchmark | Mistral 7B | Qwen1.5-32B |
|---|---|---|
| LMArena Longer Query | 1060 | 1146 |
Writing & Preference Qwen1.5-32B leads
Mistral 7B: 30.7 (#286), Qwen1.5-32B: 34.2 (#271)
| Benchmark | Mistral 7B | Qwen1.5-32B |
|---|---|---|
| LMArena Text | 1090 | 1137 |
| LMArena Creative Writing | 1068 | 1083 |
| LMArena Multi-Turn | 1062 | 1140 |
Frequently asked questions
Is Mistral 7B better than Qwen1.5-32B?
Qwen1.5-32B is the stronger model overall, scoring 30.5 to 23.0 on the Noometry Index.
Is Mistral 7B or Qwen1.5-32B better for coding?
Qwen1.5-32B scores higher on coding benchmarks: 31.7 versus 26.4 in the Noometry coding category.
How many benchmarks do Mistral 7B and Qwen1.5-32B share?
20 benchmarks have published results for both models. Mistral 7B has 37 scored results on Noometry and Qwen1.5-32B has 21.