Model comparison
o1-mini vs Qwen1.5-32B
o1-mini is the stronger model overall, scoring 34.0 to 30.5 on the Noometry Index.
Last verified . 18 shared benchmarks.
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. o1-mini scores higher in 7 categories and Qwen1.5-32B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where o1-mini leads 34.9 to 13.5.
- The biggest single-benchmark swing is GPQA Diamond: 62.4% for o1-mini and 30.7% for Qwen1.5-32B.
- Qwen1.5-32B has downloadable open weights; the other is API-only.
Side by side
| o1-mini | Qwen1.5-32B | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 34.0 | 30.5 |
| Released | 2024-09-12 | 2024-02-04 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 39 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o1-mini leads
o1-mini: 35.5 (#224), Qwen1.5-32B: 31.7 (#282)
| Benchmark | o1-mini | Qwen1.5-32B |
|---|---|---|
| LMArena Coding | 1362 | 1155 |
| Aider Polyglot | 32.9% | — |
| WeirdML | 36.3% | — |
| BigCodeBench Instruct | — | 32.3% |
| LiveBench Coding | 48% | — |
| BigCodeBench Complete | — | 42% |
| HumanEval+ | 89% | — |
| MBPP+ | 78.8% | — |
Agentic & Tool Use Not comparable
o1-mini: 24.6 (#118), Qwen1.5-32B: —
| Benchmark | o1-mini | Qwen1.5-32B |
|---|---|---|
| Cybench | 10% | — |
Reasoning Qwen1.5-32B leads
o1-mini: 8.8 (#346), Qwen1.5-32B: 21.8 (#212)
| Benchmark | o1-mini | Qwen1.5-32B |
|---|---|---|
| LMArena Hard Prompts | 1333 | 1130 |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 18.1% | — |
| ARC-AGI-1 | 14% | — |
| LiveBench Reasoning | 72.3% | — |
| LiveBench Data Analysis | 57.9% | — |
| Epoch Capabilities Index | 135.82 | — |
| LiveBench | 57.8% | — |
Math o1-mini leads
o1-mini: 35.4 (#186), Qwen1.5-32B: 33.0 (#207)
| Benchmark | o1-mini | Qwen1.5-32B |
|---|---|---|
| LMArena Math | 1358 | 1155 |
| OTIS Mock AIME 2024-2025 | 46.9% | — |
| LiveBench Math | 62% | — |
| MATH Level 5 | 89.2% | — |
| FrontierMath (Feb 2025 set) | 1.7% | — |
Knowledge o1-mini leads
o1-mini: 34.9 (#192), Qwen1.5-32B: 13.5 (#296)
| Benchmark | o1-mini | Qwen1.5-32B |
|---|---|---|
| GPQA Diamond | 62.4% | 30.7% |
| LMArena Expert | 1316 | 1126 |
| Confabulations | 18.6% | — |
| MMLU | — | 74.4% |
Multilingual o1-mini leads
o1-mini: 43.6 (#182), Qwen1.5-32B: 31.4 (#259)
| Benchmark | o1-mini | Qwen1.5-32B |
|---|---|---|
| LMArena Non-English | 1289 | 1106 |
| LMArena Chinese | 1314 | 1177 |
| LMArena French | 1293 | 1101 |
| LMArena German | 1278 | 1058 |
| LMArena Japanese | 1245 | 1027 |
| LMArena Korean | 1223 | 1008 |
| LMArena Russian | 1283 | 1073 |
| LMArena Spanish | 1303 | 1089 |
Instruction Following o1-mini leads
o1-mini: 66.7 (#206), Qwen1.5-32B: 57.7 (#265)
| Benchmark | o1-mini | Qwen1.5-32B |
|---|---|---|
| LMArena Instruction Following | 1304 | 1116 |
| LiveBench Instruction Following | 65.4% | — |
Long Context o1-mini leads
o1-mini: 40.1 (#161), Qwen1.5-32B: 34.7 (#246)
| Benchmark | o1-mini | Qwen1.5-32B |
|---|---|---|
| LMArena Longer Query | 1320 | 1146 |
Writing & Preference o1-mini leads
o1-mini: 48.4 (#202), Qwen1.5-32B: 34.2 (#271)
| Benchmark | o1-mini | Qwen1.5-32B |
|---|---|---|
| LMArena Text | 1317 | 1137 |
| LMArena Creative Writing | 1244 | 1083 |
| LMArena Multi-Turn | 1314 | 1140 |
| Short-Story Creative Writing | 64.9% | — |
| LiveBench Language | 40.9% | — |
Frequently asked questions
Is o1-mini better than Qwen1.5-32B?
o1-mini is the stronger model overall, scoring 34.0 to 30.5 on the Noometry Index.
Is o1-mini or Qwen1.5-32B better for coding?
o1-mini scores higher on coding benchmarks: 35.5 versus 31.7 in the Noometry coding category.
How many benchmarks do o1-mini and Qwen1.5-32B share?
18 benchmarks have published results for both models. o1-mini has 39 scored results on Noometry and Qwen1.5-32B has 21.