Model comparison
Qwen2-72B vs QwQ-32B
QwQ-32B is the stronger model overall, scoring 39.8 to 30.0 on the Noometry Index.
Last verified . 21 shared benchmarks.
Alibaba (Qwen)Summary
- They share 21 benchmarks with published results for both. Qwen2-72B scores higher in 0 categories and QwQ-32B in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where QwQ-32B leads 37.2 to 21.2.
- The biggest single-benchmark swing is GPQA Diamond: 40.8% for Qwen2-72B and 65.3% for QwQ-32B.
Side by side
| Qwen2-72B | QwQ-32B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 30.0 | 39.8 |
| Released | 2024-06-07 | 2024-11-28 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 26 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding QwQ-32B leads
Qwen2-72B: 29.1 (#310), QwQ-32B: 35.4 (#226)
| Benchmark | Qwen2-72B | QwQ-32B |
|---|---|---|
| BigCodeBench Instruct | 38.5% | 44.6% |
| LMArena Coding | 1196 | 1333 |
| BigCodeBench Complete | 54% | 54.4% |
| Aider Polyglot | — | 20.9% |
| WeirdML | 11.3% | — |
| LiveBench Coding | — | 72.2% |
Agentic & Tool Use Not comparable
Qwen2-72B: 17.0 (#146), QwQ-32B: —
| Benchmark | Qwen2-72B | QwQ-32B |
|---|---|---|
| TheAgentCompany | 1.1% | — |
| METR Time Horizons | 29.9% | — |
Reasoning Too close to call
Qwen2-72B: 23.2 (#181), QwQ-32B: 23.7 (#174)
| Benchmark | Qwen2-72B | QwQ-32B |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1325 |
| Epoch Capabilities Index | 125.28 | 137.6 |
| Chess Puzzles | — | 5% |
| LiveBench Reasoning | — | 83.5% |
| LiveBench Data Analysis | — | 65% |
| ForecastBench | — | 58.3 |
| LiveBench | — | 72% |
Math QwQ-32B leads
Qwen2-72B: 30.2 (#236), QwQ-32B: 38.0 (#143)
| Benchmark | Qwen2-72B | QwQ-32B |
|---|---|---|
| LMArena Math | 1235 | 1359 |
| OTIS Mock AIME 2024-2025 | — | 59.2% |
| LiveBench Math | — | 77.8% |
| MATH Level 5 | 39.1% | — |
Knowledge QwQ-32B leads
Qwen2-72B: 21.2 (#275), QwQ-32B: 37.2 (#158)
| Benchmark | Qwen2-72B | QwQ-32B |
|---|---|---|
| GPQA Diamond | 40.8% | 65.3% |
| LMArena Expert | 1171 | 1324 |
| Confabulations | — | 15.6% |
| MMLU | 82.4% | — |
Multilingual QwQ-32B leads
Qwen2-72B: 35.9 (#244), QwQ-32B: 44.8 (#176)
| Benchmark | Qwen2-72B | QwQ-32B |
|---|---|---|
| LMArena Non-English | 1176 | 1305 |
| LMArena Chinese | 1240 | 1378 |
| LMArena French | 1170 | 1336 |
| LMArena German | 1151 | 1313 |
| LMArena Japanese | 1111 | 1262 |
| LMArena Korean | 1083 | 1279 |
| LMArena Russian | 1169 | 1297 |
| LMArena Spanish | 1169 | 1354 |
Instruction Following QwQ-32B leads
Qwen2-72B: 61.7 (#241), QwQ-32B: 72.6 (#137)
| Benchmark | Qwen2-72B | QwQ-32B |
|---|---|---|
| LMArena Instruction Following | 1181 | 1297 |
| LiveBench Instruction Following | — | 81.8% |
Long Context QwQ-32B leads
Qwen2-72B: 36.1 (#235), QwQ-32B: 49.0 (#11)
| Benchmark | Qwen2-72B | QwQ-32B |
|---|---|---|
| LMArena Longer Query | 1192 | 1308 |
| Fiction.LiveBench | — | 83.3% |
Writing & Preference QwQ-32B leads
Qwen2-72B: 40.8 (#241), QwQ-32B: 50.6 (#180)
| Benchmark | Qwen2-72B | QwQ-32B |
|---|---|---|
| LMArena Text | 1203 | 1329 |
| LMArena Creative Writing | 1181 | 1288 |
| LMArena Multi-Turn | 1196 | 1314 |
| Short-Story Creative Writing | — | 80.2% |
| EQ-Bench Creative Writing | — | 1257 |
| LiveBench Language | — | 51.4% |
Frequently asked questions
Is Qwen2-72B better than QwQ-32B?
QwQ-32B is the stronger model overall, scoring 39.8 to 30.0 on the Noometry Index.
Is Qwen2-72B or QwQ-32B better for coding?
QwQ-32B scores higher on coding benchmarks: 35.4 versus 29.1 in the Noometry coding category.
How many benchmarks do Qwen2-72B and QwQ-32B share?
21 benchmarks have published results for both models. Qwen2-72B has 26 scored results on Noometry and QwQ-32B has 36.