Model comparison
Mistral 7B vs Qwen2.5 32B Instruct
Qwen2.5 32B Instruct is the stronger model overall, scoring 30.1 to 23.0 on the Noometry Index. Mistral 7B costs 4.9× less per token, which makes it the better buy when Qwen2.5 32B Instruct's lead doesn't matter for your workload.
Last verified . 7 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 7 benchmarks with published results for both. Mistral 7B scores higher in 0 categories and Qwen2.5 32B Instruct in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen2.5 32B Instruct leads 24.9 to 7.4.
- The biggest single-benchmark swing is MATH Level 5: 3.7% for Mistral 7B and 56.1% for Qwen2.5 32B Instruct.
- Mistral 7B is cheaper at $0.25 / $0.25 per million input/output tokens, against $0.70 / $2.80 for Qwen2.5 32B Instruct.
- Qwen2.5 32B Instruct accepts more context: 131K tokens versus 8K.
Side by side
| Mistral 7B | Qwen2.5 32B Instruct | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 23.0 | 30.1 |
| Released | 2023-09-27 | 2024-09 |
| Weights | Open | Open |
| Context window | 8K | 131K |
| Max output | 8K | 8K |
| Input $ / M tokens | $0.25 | $0.70 |
| Output $ / M tokens | $0.25 | $2.80 |
| Results tracked | 37 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5 32B Instruct leads
Mistral 7B: 26.4 (#326), Qwen2.5 32B Instruct: 38.7 (#169)
| Benchmark | Mistral 7B | Qwen2.5 32B Instruct |
|---|---|---|
| BigCodeBench Instruct | 19.5% | 45% |
| BigCodeBench Complete | 27.3% | 52.3% |
| LMArena Coding | 1082 | — |
| HumanEval+ | 36% | — |
| MBPP+ | 42.1% | — |
Reasoning Qwen2.5 32B Instruct leads
Mistral 7B: 13.1 (#336), Qwen2.5 32B Instruct: 19.2 (#266)
| Benchmark | Mistral 7B | Qwen2.5 32B Instruct |
|---|---|---|
| Chess Puzzles | 0% | 0% |
| Epoch Capabilities Index | 112.21 | 128.52 |
| LMArena Hard Prompts | 1067 | — |
| DTBench | 42.5% | — |
| Adversarial NLI | 47.1% | — |
| BIG-Bench Hard | 56.1% | — |
| HellaSwag | 81% | — |
| PIQA | 83% | — |
| WinoGrande | 75.3% | — |
Math Qwen2.5 32B Instruct leads
Mistral 7B: 8.1 (#325), Qwen2.5 32B Instruct: 16.2 (#296)
| Benchmark | Mistral 7B | Qwen2.5 32B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.3% | 7.4% |
| MATH Level 5 | 3.7% | 56.1% |
| LMArena Math | 1085 | — |
| GSM8K | 54.4% | — |
Knowledge Qwen2.5 32B Instruct leads
Mistral 7B: 7.4 (#311), Qwen2.5 32B Instruct: 24.9 (#266)
| Benchmark | Mistral 7B | Qwen2.5 32B Instruct |
|---|---|---|
| GPQA Diamond | 15.2% | 46.1% |
| LMArena Expert | 1036 | — |
| ARC (AI2) Challenge | 78.6% | — |
| BoolQ | 87.4% | — |
| MMLU | 62.5% | — |
| OpenBookQA | 79.8% | — |
| TriviaQA | 75.2% | — |
Multilingual Not comparable
Mistral 7B: 25.8 (#283), Qwen2.5 32B Instruct: —
| Benchmark | Mistral 7B | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Non-English | 1012 | — |
| LMArena Chinese | 1009 | — |
| LMArena French | 1037 | — |
| LMArena German | 987 | — |
| LMArena Japanese | 878 | — |
| LMArena Russian | 1018 | — |
| LMArena Spanish | 1026 | — |
Instruction Following Not comparable
Mistral 7B: 54.2 (#280), Qwen2.5 32B Instruct: —
| Benchmark | Mistral 7B | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Instruction Following | 1060 | — |
Long Context Not comparable
Mistral 7B: 32.2 (#271), Qwen2.5 32B Instruct: —
| Benchmark | Mistral 7B | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Longer Query | 1060 | — |
Writing & Preference Not comparable
Mistral 7B: 30.7 (#286), Qwen2.5 32B Instruct: —
| Benchmark | Mistral 7B | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Text | 1090 | — |
| LMArena Creative Writing | 1068 | — |
| LMArena Multi-Turn | 1062 | — |
Frequently asked questions
Is Mistral 7B better than Qwen2.5 32B Instruct?
Qwen2.5 32B Instruct is the stronger model overall, scoring 30.1 to 23.0 on the Noometry Index. Mistral 7B costs 4.9× less per token, which makes it the better buy when Qwen2.5 32B Instruct's lead doesn't matter for your workload.
Which is cheaper, Mistral 7B or Qwen2.5 32B Instruct?
Mistral 7B is cheaper. It lists at $0.25 per million input tokens and $0.25 per million output tokens; Qwen2.5 32B Instruct lists at $0.70 and $2.80.
Is Mistral 7B or Qwen2.5 32B Instruct better for coding?
Qwen2.5 32B Instruct scores higher on coding benchmarks: 38.7 versus 26.4 in the Noometry coding category.
Which has the bigger context window?
Qwen2.5 32B Instruct does, with 131K tokens against 8K.
How many benchmarks do Mistral 7B and Qwen2.5 32B Instruct share?
7 benchmarks have published results for both models. Mistral 7B has 37 scored results on Noometry and Qwen2.5 32B Instruct has 7.