Model comparison
o1-mini vs QwQ-32B
QwQ-32B is the stronger model overall, scoring 39.8 to 34.0 on the Noometry Index.
Last verified . 30 shared benchmarks.
Alibaba (Qwen)Summary
- They share 30 benchmarks with published results for both. o1-mini scores higher in 1 category and QwQ-32B in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where QwQ-32B leads 23.7 to 8.8.
- The biggest single-benchmark swing is LiveBench Coding: 48% for o1-mini and 72.2% for QwQ-32B.
- QwQ-32B has downloadable open weights; the other is API-only.
Side by side
| o1-mini | QwQ-32B | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 34.0 | 39.8 |
| Released | 2024-09-12 | 2024-11-28 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 39 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
o1-mini: 35.5 (#224), QwQ-32B: 35.4 (#226)
| Benchmark | o1-mini | QwQ-32B |
|---|---|---|
| Aider Polyglot | 32.9% | 20.9% |
| LiveBench Coding | 48% | 72.2% |
| LMArena Coding | 1362 | 1333 |
| WeirdML | 36.3% | — |
| BigCodeBench Instruct | — | 44.6% |
| BigCodeBench Complete | — | 54.4% |
| HumanEval+ | 89% | — |
| MBPP+ | 78.8% | — |
Agentic & Tool Use Not comparable
o1-mini: 24.6 (#118), QwQ-32B: —
| Benchmark | o1-mini | QwQ-32B |
|---|---|---|
| Cybench | 10% | — |
Reasoning QwQ-32B leads
o1-mini: 8.8 (#346), QwQ-32B: 23.7 (#174)
| Benchmark | o1-mini | QwQ-32B |
|---|---|---|
| LiveBench Reasoning | 72.3% | 83.5% |
| LMArena Hard Prompts | 1333 | 1325 |
| LiveBench Data Analysis | 57.9% | 65% |
| Epoch Capabilities Index | 135.82 | 137.6 |
| LiveBench | 57.8% | 72% |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 18.1% | — |
| ARC-AGI-1 | 14% | — |
| Chess Puzzles | — | 5% |
| ForecastBench | — | 58.3 |
Math QwQ-32B leads
o1-mini: 35.4 (#186), QwQ-32B: 38.0 (#143)
| Benchmark | o1-mini | QwQ-32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 46.9% | 59.2% |
| LiveBench Math | 62% | 77.8% |
| LMArena Math | 1358 | 1359 |
| MATH Level 5 | 89.2% | — |
| FrontierMath (Feb 2025 set) | 1.7% | — |
Knowledge QwQ-32B leads
o1-mini: 34.9 (#192), QwQ-32B: 37.2 (#158)
| Benchmark | o1-mini | QwQ-32B |
|---|---|---|
| GPQA Diamond | 62.4% | 65.3% |
| Confabulations | 18.6% | 15.6% |
| LMArena Expert | 1316 | 1324 |
Multilingual QwQ-32B leads
o1-mini: 43.6 (#182), QwQ-32B: 44.8 (#176)
| Benchmark | o1-mini | QwQ-32B |
|---|---|---|
| LMArena Non-English | 1289 | 1305 |
| LMArena Chinese | 1314 | 1378 |
| LMArena French | 1293 | 1336 |
| LMArena German | 1278 | 1313 |
| LMArena Japanese | 1245 | 1262 |
| LMArena Korean | 1223 | 1279 |
| LMArena Russian | 1283 | 1297 |
| LMArena Spanish | 1303 | 1354 |
Instruction Following QwQ-32B leads
o1-mini: 66.7 (#206), QwQ-32B: 72.6 (#137)
| Benchmark | o1-mini | QwQ-32B |
|---|---|---|
| LiveBench Instruction Following | 65.4% | 81.8% |
| LMArena Instruction Following | 1304 | 1297 |
Long Context QwQ-32B leads
o1-mini: 40.1 (#161), QwQ-32B: 49.0 (#11)
| Benchmark | o1-mini | QwQ-32B |
|---|---|---|
| LMArena Longer Query | 1320 | 1308 |
| Fiction.LiveBench | — | 83.3% |
Writing & Preference QwQ-32B leads
o1-mini: 48.4 (#202), QwQ-32B: 50.6 (#180)
| Benchmark | o1-mini | QwQ-32B |
|---|---|---|
| LMArena Text | 1317 | 1329 |
| LMArena Creative Writing | 1244 | 1288 |
| Short-Story Creative Writing | 64.9% | 80.2% |
| LMArena Multi-Turn | 1314 | 1314 |
| LiveBench Language | 40.9% | 51.4% |
| EQ-Bench Creative Writing | — | 1257 |
Frequently asked questions
Is o1-mini better than QwQ-32B?
QwQ-32B is the stronger model overall, scoring 39.8 to 34.0 on the Noometry Index.
Is o1-mini or QwQ-32B better for coding?
They score almost the same on coding (35.5 vs 35.4); test both on your own repository before choosing.
How many benchmarks do o1-mini and QwQ-32B share?
30 benchmarks have published results for both models. o1-mini has 39 scored results on Noometry and QwQ-32B has 36.