Model comparison
Llama 2-7B vs QwQ-32B
QwQ-32B is the stronger model overall, scoring 39.8 to 29.1 on the Noometry Index.
Last verified . 17 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Llama 2-7B scores higher in 0 categories and QwQ-32B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where QwQ-32B leads 50.6 to 28.0.
- The biggest single-benchmark swing is Chess Puzzles: 0% for Llama 2-7B and 5% for QwQ-32B.
Side by side
| Llama 2-7B | QwQ-32B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 29.1 | 39.8 |
| Released | 2023-07-18 | 2024-11-28 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 29 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding QwQ-32B leads
Llama 2-7B: 29.2 (#307), QwQ-32B: 35.4 (#226)
| Benchmark | Llama 2-7B | QwQ-32B |
|---|---|---|
| LMArena Coding | 1002 | 1333 |
| Aider Polyglot | — | 20.9% |
| BigCodeBench Instruct | — | 44.6% |
| LiveBench Coding | — | 72.2% |
| BigCodeBench Complete | — | 54.4% |
Reasoning QwQ-32B leads
Llama 2-7B: 15.7 (#312), QwQ-32B: 23.7 (#174)
| Benchmark | Llama 2-7B | QwQ-32B |
|---|---|---|
| Chess Puzzles | 0% | 5% |
| LMArena Hard Prompts | 1009 | 1325 |
| Epoch Capabilities Index | 99.06 | 137.6 |
| LiveBench Reasoning | — | 83.5% |
| LiveBench Data Analysis | — | 65% |
| BIG-Bench Hard | 39.2% | — |
| ForecastBench | — | 58.3 |
| HellaSwag | 77.2% | — |
| LAMBADA | 73.3% | — |
| LiveBench | — | 72% |
| PIQA | 78.8% | — |
| WinoGrande | 69.2% | — |
Math QwQ-32B leads
Llama 2-7B: 30.7 (#233), QwQ-32B: 38.0 (#143)
| Benchmark | Llama 2-7B | QwQ-32B |
|---|---|---|
| LMArena Math | 1042 | 1359 |
| OTIS Mock AIME 2024-2025 | — | 59.2% |
| LiveBench Math | — | 77.8% |
| GSM8K | 16.7% | — |
Knowledge QwQ-32B leads
Llama 2-7B: 28.2 (#248), QwQ-32B: 37.2 (#158)
| Benchmark | Llama 2-7B | QwQ-32B |
|---|---|---|
| LMArena Expert | 1036 | 1324 |
| GPQA Diamond | — | 65.3% |
| Confabulations | — | 15.6% |
| ARC (AI2) Challenge | 45.9% | — |
| BoolQ | 77.9% | — |
| MMLU | 45.8% | — |
| OpenBookQA | 58.6% | — |
| TriviaQA | 73.7% | — |
Multimodal Not comparable
Llama 2-7B: —, QwQ-32B: —
| Benchmark | Llama 2-7B | QwQ-32B |
|---|---|---|
| ScienceQA | 43.1% | — |
Multilingual QwQ-32B leads
Llama 2-7B: 23.8 (#293), QwQ-32B: 44.8 (#176)
| Benchmark | Llama 2-7B | QwQ-32B |
|---|---|---|
| LMArena Non-English | 973 | 1305 |
| LMArena Chinese | 973 | 1378 |
| LMArena French | 970 | 1336 |
| LMArena German | 978 | 1313 |
| LMArena Russian | 995 | 1297 |
| LMArena Spanish | 1007 | 1354 |
| LMArena Japanese | — | 1262 |
| LMArena Korean | — | 1279 |
Instruction Following QwQ-32B leads
Llama 2-7B: 50.8 (#298), QwQ-32B: 72.6 (#137)
| Benchmark | Llama 2-7B | QwQ-32B |
|---|---|---|
| LMArena Instruction Following | 1006 | 1297 |
| LiveBench Instruction Following | — | 81.8% |
Long Context QwQ-32B leads
Llama 2-7B: 30.4 (#287), QwQ-32B: 49.0 (#11)
| Benchmark | Llama 2-7B | QwQ-32B |
|---|---|---|
| LMArena Longer Query | 999 | 1308 |
| Fiction.LiveBench | — | 83.3% |
Writing & Preference QwQ-32B leads
Llama 2-7B: 28.0 (#298), QwQ-32B: 50.6 (#180)
| Benchmark | Llama 2-7B | QwQ-32B |
|---|---|---|
| LMArena Text | 1053 | 1329 |
| LMArena Creative Writing | 1033 | 1288 |
| LMArena Multi-Turn | 1029 | 1314 |
| Short-Story Creative Writing | — | 80.2% |
| EQ-Bench Creative Writing | — | 1257 |
| LiveBench Language | — | 51.4% |
Frequently asked questions
Is Llama 2-7B better than QwQ-32B?
QwQ-32B is the stronger model overall, scoring 39.8 to 29.1 on the Noometry Index.
Is Llama 2-7B or QwQ-32B better for coding?
QwQ-32B scores higher on coding benchmarks: 35.4 versus 29.2 in the Noometry coding category.
How many benchmarks do Llama 2-7B and QwQ-32B share?
17 benchmarks have published results for both models. Llama 2-7B has 29 scored results on Noometry and QwQ-32B has 36.