Model comparison
o3-pro vs QwQ-32B
o3-pro is the stronger model overall, scoring 42.9 to 39.8 on the Noometry Index.
Last verified . 5 shared benchmarks.
Alibaba (Qwen)Summary
- They share 5 benchmarks with published results for both. o3-pro scores higher in 4 categories and QwQ-32B in 1 category; 4 gaps are clear of the uncertainty.
- The widest gap is in long context, where o3-pro leads 72.2 to 49.0.
- The biggest single-benchmark swing is Aider Polyglot: 84.9% for o3-pro and 20.9% for QwQ-32B.
- QwQ-32B has downloadable open weights; the other is API-only.
Side by side
| o3-pro | QwQ-32B | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 42.9 | 39.8 |
| Released | 2025-06-10 | 2024-11-28 |
| Weights | Proprietary | Open |
| Context window | 200K | — |
| Max output | 100K | — |
| Input $ / M tokens | $20 | — |
| Output $ / M tokens | $80 | — |
| Results tracked | 12 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-pro leads
o3-pro: 55.5 (#24), QwQ-32B: 35.4 (#226)
| Benchmark | o3-pro | QwQ-32B |
|---|---|---|
| Aider Polyglot | 84.9% | 20.9% |
| WeirdML | 58.2% | — |
| BigCodeBench Instruct | — | 44.6% |
| LiveBench Coding | — | 72.2% |
| LMArena Coding | — | 1333 |
| BigCodeBench Complete | — | 54.4% |
Reasoning Too close to call
o3-pro: 23.8 (#171), QwQ-32B: 23.7 (#174)
| Benchmark | o3-pro | QwQ-32B |
|---|---|---|
| Epoch Capabilities Index | 147.42 | 137.6 |
| ARC-AGI-2 | 4.9% | — |
| Kagi LLM Benchmark | 72.1% | — |
| ARC-AGI-1 | 59.3% | — |
| Chess Puzzles | — | 5% |
| LiveBench Reasoning | — | 83.5% |
| LMArena Hard Prompts | — | 1325 |
| DTBench | 86.9% | — |
| LiveBench Data Analysis | — | 65% |
| LMCA | 38.5% | — |
| ForecastBench | — | 58.3 |
| LiveBench | — | 72% |
Math Not comparable
o3-pro: —, QwQ-32B: 38.0 (#143)
| Benchmark | o3-pro | QwQ-32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 59.2% |
| LiveBench Math | — | 77.8% |
| LMArena Math | — | 1359 |
Knowledge QwQ-32B leads
o3-pro: 29.5 (#238), QwQ-32B: 37.2 (#158)
| Benchmark | o3-pro | QwQ-32B |
|---|---|---|
| Confabulations | 14.2% | 15.6% |
| GPQA Diamond | — | 65.3% |
| Vectara Hallucination Rate | 23.3% | — |
| LMArena Expert | — | 1324 |
Multilingual Not comparable
o3-pro: —, QwQ-32B: 44.8 (#176)
| Benchmark | o3-pro | QwQ-32B |
|---|---|---|
| LMArena Non-English | — | 1305 |
| LMArena Chinese | — | 1378 |
| LMArena French | — | 1336 |
| LMArena German | — | 1313 |
| LMArena Japanese | — | 1262 |
| LMArena Korean | — | 1279 |
| LMArena Russian | — | 1297 |
| LMArena Spanish | — | 1354 |
Instruction Following Not comparable
o3-pro: —, QwQ-32B: 72.6 (#137)
| Benchmark | o3-pro | QwQ-32B |
|---|---|---|
| LiveBench Instruction Following | — | 81.8% |
| LMArena Instruction Following | — | 1297 |
Long Context o3-pro leads
o3-pro: 72.2 (#1), QwQ-32B: 49.0 (#11)
| Benchmark | o3-pro | QwQ-32B |
|---|---|---|
| Fiction.LiveBench | 97.2% | 83.3% |
| LMArena Longer Query | — | 1308 |
Writing & Preference o3-pro leads
o3-pro: 57.1 (#133), QwQ-32B: 50.6 (#180)
| Benchmark | o3-pro | QwQ-32B |
|---|---|---|
| Short-Story Creative Writing | 84.4% | 80.2% |
| LMArena Text | — | 1329 |
| LMArena Creative Writing | — | 1288 |
| EQ-Bench Creative Writing | — | 1257 |
| LMArena Multi-Turn | — | 1314 |
| LiveBench Language | — | 51.4% |
Frequently asked questions
Is o3-pro better than QwQ-32B?
o3-pro is the stronger model overall, scoring 42.9 to 39.8 on the Noometry Index.
Is o3-pro or QwQ-32B better for coding?
o3-pro scores higher on coding benchmarks: 55.5 versus 35.4 in the Noometry coding category.
How many benchmarks do o3-pro and QwQ-32B share?
5 benchmarks have published results for both models. o3-pro has 12 scored results on Noometry and QwQ-32B has 36.