Model comparison
Mistral 7B vs Qwen2-72B
Qwen2-72B is the stronger model overall, scoring 30.0 to 23.0 on the Noometry Index.
Last verified . 22 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 22 benchmarks with published results for both. Mistral 7B scores higher in 0 categories and Qwen2-72B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen2-72B leads 30.2 to 8.1.
- The biggest single-benchmark swing is MATH Level 5: 3.7% for Mistral 7B and 39.1% for Qwen2-72B.
Side by side
| Mistral 7B | Qwen2-72B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 23.0 | 30.0 |
| Released | 2023-09-27 | 2024-06-07 |
| Weights | Open | Open |
| Context window | 8K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $0.25 | — |
| Results tracked | 37 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2-72B leads
Mistral 7B: 26.4 (#326), Qwen2-72B: 29.1 (#310)
| Benchmark | Mistral 7B | Qwen2-72B |
|---|---|---|
| BigCodeBench Instruct | 19.5% | 38.5% |
| LMArena Coding | 1082 | 1196 |
| BigCodeBench Complete | 27.3% | 54% |
| WeirdML | — | 11.3% |
| HumanEval+ | 36% | — |
| MBPP+ | 42.1% | — |
Agentic & Tool Use Not comparable
Mistral 7B: —, Qwen2-72B: 17.0 (#146)
| Benchmark | Mistral 7B | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
Reasoning Qwen2-72B leads
Mistral 7B: 13.1 (#336), Qwen2-72B: 23.2 (#181)
| Benchmark | Mistral 7B | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1067 | 1191 |
| Epoch Capabilities Index | 112.21 | 125.28 |
| Chess Puzzles | 0% | — |
| DTBench | 42.5% | — |
| Adversarial NLI | 47.1% | — |
| BIG-Bench Hard | 56.1% | — |
| HellaSwag | 81% | — |
| PIQA | 83% | — |
| WinoGrande | 75.3% | — |
Math Qwen2-72B leads
Mistral 7B: 8.1 (#325), Qwen2-72B: 30.2 (#236)
| Benchmark | Mistral 7B | Qwen2-72B |
|---|---|---|
| LMArena Math | 1085 | 1235 |
| MATH Level 5 | 3.7% | 39.1% |
| OTIS Mock AIME 2024-2025 | 0.3% | — |
| GSM8K | 54.4% | — |
Knowledge Qwen2-72B leads
Mistral 7B: 7.4 (#311), Qwen2-72B: 21.2 (#275)
| Benchmark | Mistral 7B | Qwen2-72B |
|---|---|---|
| GPQA Diamond | 15.2% | 40.8% |
| LMArena Expert | 1036 | 1171 |
| MMLU | 62.5% | 82.4% |
| ARC (AI2) Challenge | 78.6% | — |
| BoolQ | 87.4% | — |
| OpenBookQA | 79.8% | — |
| TriviaQA | 75.2% | — |
Multilingual Qwen2-72B leads
Mistral 7B: 25.8 (#283), Qwen2-72B: 35.9 (#244)
| Benchmark | Mistral 7B | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1012 | 1176 |
| LMArena Chinese | 1009 | 1240 |
| LMArena French | 1037 | 1170 |
| LMArena German | 987 | 1151 |
| LMArena Japanese | 878 | 1111 |
| LMArena Russian | 1018 | 1169 |
| LMArena Spanish | 1026 | 1169 |
| LMArena Korean | — | 1083 |
Instruction Following Qwen2-72B leads
Mistral 7B: 54.2 (#280), Qwen2-72B: 61.7 (#241)
| Benchmark | Mistral 7B | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1060 | 1181 |
Long Context Qwen2-72B leads
Mistral 7B: 32.2 (#271), Qwen2-72B: 36.1 (#235)
| Benchmark | Mistral 7B | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1060 | 1192 |
Writing & Preference Qwen2-72B leads
Mistral 7B: 30.7 (#286), Qwen2-72B: 40.8 (#241)
| Benchmark | Mistral 7B | Qwen2-72B |
|---|---|---|
| LMArena Text | 1090 | 1203 |
| LMArena Creative Writing | 1068 | 1181 |
| LMArena Multi-Turn | 1062 | 1196 |
Frequently asked questions
Is Mistral 7B better than Qwen2-72B?
Qwen2-72B is the stronger model overall, scoring 30.0 to 23.0 on the Noometry Index.
Is Mistral 7B or Qwen2-72B better for coding?
Qwen2-72B scores higher on coding benchmarks: 29.1 versus 26.4 in the Noometry coding category.
How many benchmarks do Mistral 7B and Qwen2-72B share?
22 benchmarks have published results for both models. Mistral 7B has 37 scored results on Noometry and Qwen2-72B has 26.