Model comparison
Mistral 7B vs QwQ-32B
QwQ-32B is the stronger model overall, scoring 39.8 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 QwQ-32B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where QwQ-32B leads 37.2 to 7.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.3% for Mistral 7B and 59.2% for QwQ-32B.
Side by side
| Mistral 7B | QwQ-32B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 23.0 | 39.8 |
| Released | 2023-09-27 | 2024-11-28 |
| Weights | Open | Open |
| Context window | 8K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $0.25 | — |
| Results tracked | 37 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding QwQ-32B leads
Mistral 7B: 26.4 (#326), QwQ-32B: 35.4 (#226)
| Benchmark | Mistral 7B | QwQ-32B |
|---|---|---|
| BigCodeBench Instruct | 19.5% | 44.6% |
| LMArena Coding | 1082 | 1333 |
| BigCodeBench Complete | 27.3% | 54.4% |
| Aider Polyglot | — | 20.9% |
| LiveBench Coding | — | 72.2% |
| HumanEval+ | 36% | — |
| MBPP+ | 42.1% | — |
Reasoning QwQ-32B leads
Mistral 7B: 13.1 (#336), QwQ-32B: 23.7 (#174)
| Benchmark | Mistral 7B | QwQ-32B |
|---|---|---|
| Chess Puzzles | 0% | 5% |
| LMArena Hard Prompts | 1067 | 1325 |
| Epoch Capabilities Index | 112.21 | 137.6 |
| LiveBench Reasoning | — | 83.5% |
| DTBench | 42.5% | — |
| LiveBench Data Analysis | — | 65% |
| Adversarial NLI | 47.1% | — |
| BIG-Bench Hard | 56.1% | — |
| ForecastBench | — | 58.3 |
| HellaSwag | 81% | — |
| LiveBench | — | 72% |
| PIQA | 83% | — |
| WinoGrande | 75.3% | — |
Math QwQ-32B leads
Mistral 7B: 8.1 (#325), QwQ-32B: 38.0 (#143)
| Benchmark | Mistral 7B | QwQ-32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.3% | 59.2% |
| LMArena Math | 1085 | 1359 |
| LiveBench Math | — | 77.8% |
| MATH Level 5 | 3.7% | — |
| GSM8K | 54.4% | — |
Knowledge QwQ-32B leads
Mistral 7B: 7.4 (#311), QwQ-32B: 37.2 (#158)
| Benchmark | Mistral 7B | QwQ-32B |
|---|---|---|
| GPQA Diamond | 15.2% | 65.3% |
| LMArena Expert | 1036 | 1324 |
| Confabulations | — | 15.6% |
| ARC (AI2) Challenge | 78.6% | — |
| BoolQ | 87.4% | — |
| MMLU | 62.5% | — |
| OpenBookQA | 79.8% | — |
| TriviaQA | 75.2% | — |
Multilingual QwQ-32B leads
Mistral 7B: 25.8 (#283), QwQ-32B: 44.8 (#176)
| Benchmark | Mistral 7B | QwQ-32B |
|---|---|---|
| LMArena Non-English | 1012 | 1305 |
| LMArena Chinese | 1009 | 1378 |
| LMArena French | 1037 | 1336 |
| LMArena German | 987 | 1313 |
| LMArena Japanese | 878 | 1262 |
| LMArena Russian | 1018 | 1297 |
| LMArena Spanish | 1026 | 1354 |
| LMArena Korean | — | 1279 |
Instruction Following QwQ-32B leads
Mistral 7B: 54.2 (#280), QwQ-32B: 72.6 (#137)
| Benchmark | Mistral 7B | QwQ-32B |
|---|---|---|
| LMArena Instruction Following | 1060 | 1297 |
| LiveBench Instruction Following | — | 81.8% |
Long Context QwQ-32B leads
Mistral 7B: 32.2 (#271), QwQ-32B: 49.0 (#11)
| Benchmark | Mistral 7B | QwQ-32B |
|---|---|---|
| LMArena Longer Query | 1060 | 1308 |
| Fiction.LiveBench | — | 83.3% |
Writing & Preference QwQ-32B leads
Mistral 7B: 30.7 (#286), QwQ-32B: 50.6 (#180)
| Benchmark | Mistral 7B | QwQ-32B |
|---|---|---|
| LMArena Text | 1090 | 1329 |
| LMArena Creative Writing | 1068 | 1288 |
| LMArena Multi-Turn | 1062 | 1314 |
| Short-Story Creative Writing | — | 80.2% |
| EQ-Bench Creative Writing | — | 1257 |
| LiveBench Language | — | 51.4% |
Frequently asked questions
Is Mistral 7B better than QwQ-32B?
QwQ-32B is the stronger model overall, scoring 39.8 to 23.0 on the Noometry Index.
Is Mistral 7B or QwQ-32B better for coding?
QwQ-32B scores higher on coding benchmarks: 35.4 versus 26.4 in the Noometry coding category.
How many benchmarks do Mistral 7B and QwQ-32B share?
22 benchmarks have published results for both models. Mistral 7B has 37 scored results on Noometry and QwQ-32B has 36.