Model comparison
Mistral 7B vs Qwen1.5-7B
Qwen1.5-7B is the stronger model overall, scoring 31.4 to 23.0 on the Noometry Index.
Last verified . 13 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 13 benchmarks with published results for both. Mistral 7B scores higher in 2 categories and Qwen1.5-7B in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen1.5-7B leads 31.4 to 8.1.
Side by side
| Mistral 7B | Qwen1.5-7B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 23.0 | 31.4 |
| 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 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen1.5-7B leads
Mistral 7B: 26.4 (#326), Qwen1.5-7B: 32.2 (#276)
| Benchmark | Mistral 7B | Qwen1.5-7B |
|---|---|---|
| LMArena Coding | 1082 | 1107 |
| BigCodeBench Instruct | 19.5% | — |
| BigCodeBench Complete | 27.3% | — |
| HumanEval+ | 36% | — |
| MBPP+ | 42.1% | — |
Reasoning Qwen1.5-7B leads
Mistral 7B: 13.1 (#336), Qwen1.5-7B: 20.4 (#240)
| Benchmark | Mistral 7B | Qwen1.5-7B |
|---|---|---|
| LMArena Hard Prompts | 1067 | 1065 |
| 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 Qwen1.5-7B leads
Mistral 7B: 8.1 (#325), Qwen1.5-7B: 31.4 (#224)
| Benchmark | Mistral 7B | Qwen1.5-7B |
|---|---|---|
| LMArena Math | 1085 | 1080 |
| OTIS Mock AIME 2024-2025 | 0.3% | — |
| MATH Level 5 | 3.7% | — |
| GSM8K | 54.4% | — |
Knowledge Qwen1.5-7B leads
Mistral 7B: 7.4 (#311), Qwen1.5-7B: 28.7 (#243)
| Benchmark | Mistral 7B | Qwen1.5-7B |
|---|---|---|
| LMArena Expert | 1036 | 1055 |
| MMLU | 62.5% | 62.6% |
| GPQA Diamond | 15.2% | — |
| ARC (AI2) Challenge | 78.6% | — |
| BoolQ | 87.4% | — |
| OpenBookQA | 79.8% | — |
| TriviaQA | 75.2% | — |
Multilingual Qwen1.5-7B leads
Mistral 7B: 25.8 (#283), Qwen1.5-7B: 28.5 (#271)
| Benchmark | Mistral 7B | Qwen1.5-7B |
|---|---|---|
| LMArena Non-English | 1012 | 1058 |
| LMArena Chinese | 1009 | 1141 |
| LMArena Russian | 1018 | 1006 |
| LMArena French | 1037 | — |
| LMArena German | 987 | — |
| LMArena Japanese | 878 | — |
| LMArena Spanish | 1026 | — |
Instruction Following Too close to call
Mistral 7B: 54.2 (#280), Qwen1.5-7B: 54.1 (#281)
| Benchmark | Mistral 7B | Qwen1.5-7B |
|---|---|---|
| LMArena Instruction Following | 1060 | 1058 |
Long Context Too close to call
Mistral 7B: 32.2 (#271), Qwen1.5-7B: 33.1 (#266)
| Benchmark | Mistral 7B | Qwen1.5-7B |
|---|---|---|
| LMArena Longer Query | 1060 | 1090 |
Writing & Preference Mistral 7B leads
Mistral 7B: 30.7 (#286), Qwen1.5-7B: 29.6 (#293)
| Benchmark | Mistral 7B | Qwen1.5-7B |
|---|---|---|
| LMArena Text | 1090 | 1083 |
| LMArena Creative Writing | 1068 | 1035 |
| LMArena Multi-Turn | 1062 | 1062 |
Frequently asked questions
Is Mistral 7B better than Qwen1.5-7B?
Qwen1.5-7B is the stronger model overall, scoring 31.4 to 23.0 on the Noometry Index.
Is Mistral 7B or Qwen1.5-7B better for coding?
Qwen1.5-7B scores higher on coding benchmarks: 32.2 versus 26.4 in the Noometry coding category.
How many benchmarks do Mistral 7B and Qwen1.5-7B share?
13 benchmarks have published results for both models. Mistral 7B has 37 scored results on Noometry and Qwen1.5-7B has 13.