Model comparison
Qwen1.5-72B vs QwQ-32B
QwQ-32B is the stronger model overall, scoring 39.4 to 30.3 on the Noometry Index.
Last verified . 20 shared benchmarks.
Alibaba (Qwen)Summary
- They share 20 benchmarks with published results for both. Qwen1.5-72B 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 11.5.
- The biggest single-benchmark swing is GPQA Diamond: 28.8% for Qwen1.5-72B and 65.3% for QwQ-32B.
Side by side
| Qwen1.5-72B | QwQ-32B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 30.3 | 39.4 |
| Released | 2024-02-04 | 2024-11-28 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 22 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding QwQ-32B leads
Qwen1.5-72B: 31.4 (#272), QwQ-32B: 34.9 (#220)
| Benchmark | Qwen1.5-72B | QwQ-32B |
|---|---|---|
| BigCodeBench Instruct | 33.2% | 44.6% |
| LMArena Coding | 1166 | 1333 |
| BigCodeBench Complete | 40.3% | 54.4% |
| Aider Polyglot | — | 20.9% |
| LiveBench Coding | — | 72.2% |
| HumanEval+ | 59.1% | — |
| MBPP+ | 61.6% | — |
Reasoning QwQ-32B leads
Qwen1.5-72B: 21.2 (#201), QwQ-32B: 22.9 (#171)
| Benchmark | Qwen1.5-72B | QwQ-32B |
|---|---|---|
| LMArena Hard Prompts | 1148 | 1326 |
| Chess Puzzles | — | 5% |
| LiveBench Reasoning | — | 83.5% |
| LiveBench Data Analysis | — | 65% |
| Epoch Capabilities Index | — | 137.6 |
| ForecastBench | — | 58.3 |
| LiveBench | — | 72% |
Math QwQ-32B leads
Qwen1.5-72B: 30.7 (#205), QwQ-32B: 36.2 (#123)
| Benchmark | Qwen1.5-72B | QwQ-32B |
|---|---|---|
| LMArena Math | 1164 | 1359 |
| OTIS Mock AIME 2024-2025 | — | 59.2% |
| LiveBench Math | — | 77.8% |
Knowledge QwQ-32B leads
Qwen1.5-72B: 11.5 (#295), QwQ-32B: 37.2 (#150)
| Benchmark | Qwen1.5-72B | QwQ-32B |
|---|---|---|
| GPQA Diamond | 28.8% | 65.3% |
| LMArena Expert | 1136 | 1323 |
| Confabulations | — | 15.6% |
Multilingual QwQ-32B leads
Qwen1.5-72B: 33.4 (#248), QwQ-32B: 45.0 (#171)
| Benchmark | Qwen1.5-72B | QwQ-32B |
|---|---|---|
| LMArena Non-English | 1135 | 1306 |
| LMArena Chinese | 1186 | 1378 |
| LMArena French | 1158 | 1337 |
| LMArena German | 1084 | 1313 |
| LMArena Japanese | 1061 | 1263 |
| LMArena Korean | 1049 | 1278 |
| LMArena Russian | 1104 | 1297 |
| LMArena Spanish | 1110 | 1353 |
Instruction Following QwQ-32B leads
Qwen1.5-72B: 59.6 (#251), QwQ-32B: 72.8 (#131)
| Benchmark | Qwen1.5-72B | QwQ-32B |
|---|---|---|
| LMArena Instruction Following | 1142 | 1297 |
| LiveBench Instruction Following | — | 81.8% |
Long Context QwQ-32B leads
Qwen1.5-72B: 35.0 (#238), QwQ-32B: 49.0 (#11)
| Benchmark | Qwen1.5-72B | QwQ-32B |
|---|---|---|
| LMArena Longer Query | 1157 | 1308 |
| Fiction.LiveBench | — | 83.3% |
Writing & Preference QwQ-32B leads
Qwen1.5-72B: 37.4 (#253), QwQ-32B: 50.9 (#175)
| Benchmark | Qwen1.5-72B | QwQ-32B |
|---|---|---|
| LMArena Text | 1166 | 1329 |
| LMArena Creative Writing | 1137 | 1288 |
| LMArena Multi-Turn | 1160 | 1314 |
| Short-Story Creative Writing | — | 80.2% |
| EQ-Bench Creative Writing | — | 1257 |
| LiveBench Language | — | 51.4% |
Frequently asked questions
Is Qwen1.5-72B better than QwQ-32B?
QwQ-32B is the stronger model overall, scoring 39.4 to 30.3 on the Noometry Index.
Is Qwen1.5-72B or QwQ-32B better for coding?
QwQ-32B scores higher on coding benchmarks: 34.9 versus 31.4 in the Noometry coding category.
How many benchmarks do Qwen1.5-72B and QwQ-32B share?
20 benchmarks have published results for both models. Qwen1.5-72B has 22 scored results on Noometry and QwQ-32B has 36.