Model comparison
o1-mini vs Qwen2-72B
o1-mini is the stronger model overall, scoring 34.0 to 30.0 on the Noometry Index.
Last verified . 21 shared benchmarks.
Alibaba (Qwen)Summary
- They share 21 benchmarks with published results for both. o1-mini scores higher in 8 categories and Qwen2-72B in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen2-72B leads 23.2 to 8.8.
- The biggest single-benchmark swing is MATH Level 5: 89.2% for o1-mini and 39.1% for Qwen2-72B.
- Qwen2-72B has downloadable open weights; the other is API-only.
Side by side
| o1-mini | Qwen2-72B | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 34.0 | 30.0 |
| Released | 2024-09-12 | 2024-06-07 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 39 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o1-mini leads
o1-mini: 35.5 (#224), Qwen2-72B: 29.1 (#310)
| Benchmark | o1-mini | Qwen2-72B |
|---|---|---|
| WeirdML | 36.3% | 11.3% |
| LMArena Coding | 1362 | 1196 |
| Aider Polyglot | 32.9% | — |
| BigCodeBench Instruct | — | 38.5% |
| LiveBench Coding | 48% | — |
| BigCodeBench Complete | — | 54% |
| HumanEval+ | 89% | — |
| MBPP+ | 78.8% | — |
Agentic & Tool Use o1-mini leads
o1-mini: 24.6 (#118), Qwen2-72B: 17.0 (#146)
| Benchmark | o1-mini | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| Cybench | 10% | — |
| METR Time Horizons | — | 29.9% |
Reasoning Qwen2-72B leads
o1-mini: 8.8 (#346), Qwen2-72B: 23.2 (#181)
| Benchmark | o1-mini | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1333 | 1191 |
| Epoch Capabilities Index | 135.82 | 125.28 |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 18.1% | — |
| ARC-AGI-1 | 14% | — |
| LiveBench Reasoning | 72.3% | — |
| LiveBench Data Analysis | 57.9% | — |
| LiveBench | 57.8% | — |
Math o1-mini leads
o1-mini: 35.4 (#186), Qwen2-72B: 30.2 (#236)
| Benchmark | o1-mini | Qwen2-72B |
|---|---|---|
| LMArena Math | 1358 | 1235 |
| MATH Level 5 | 89.2% | 39.1% |
| OTIS Mock AIME 2024-2025 | 46.9% | — |
| LiveBench Math | 62% | — |
| FrontierMath (Feb 2025 set) | 1.7% | — |
Knowledge o1-mini leads
o1-mini: 34.9 (#192), Qwen2-72B: 21.2 (#275)
| Benchmark | o1-mini | Qwen2-72B |
|---|---|---|
| GPQA Diamond | 62.4% | 40.8% |
| LMArena Expert | 1316 | 1171 |
| Confabulations | 18.6% | — |
| MMLU | — | 82.4% |
Multilingual o1-mini leads
o1-mini: 43.6 (#182), Qwen2-72B: 35.9 (#244)
| Benchmark | o1-mini | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1289 | 1176 |
| LMArena Chinese | 1314 | 1240 |
| LMArena French | 1293 | 1170 |
| LMArena German | 1278 | 1151 |
| LMArena Japanese | 1245 | 1111 |
| LMArena Korean | 1223 | 1083 |
| LMArena Russian | 1283 | 1169 |
| LMArena Spanish | 1303 | 1169 |
Instruction Following o1-mini leads
o1-mini: 66.7 (#206), Qwen2-72B: 61.7 (#241)
| Benchmark | o1-mini | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1304 | 1181 |
| LiveBench Instruction Following | 65.4% | — |
Long Context o1-mini leads
o1-mini: 40.1 (#161), Qwen2-72B: 36.1 (#235)
| Benchmark | o1-mini | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1320 | 1192 |
Writing & Preference o1-mini leads
o1-mini: 48.4 (#202), Qwen2-72B: 40.8 (#241)
| Benchmark | o1-mini | Qwen2-72B |
|---|---|---|
| LMArena Text | 1317 | 1203 |
| LMArena Creative Writing | 1244 | 1181 |
| LMArena Multi-Turn | 1314 | 1196 |
| Short-Story Creative Writing | 64.9% | — |
| LiveBench Language | 40.9% | — |
Frequently asked questions
Is o1-mini better than Qwen2-72B?
o1-mini is the stronger model overall, scoring 34.0 to 30.0 on the Noometry Index.
Is o1-mini or Qwen2-72B better for coding?
o1-mini scores higher on coding benchmarks: 35.5 versus 29.1 in the Noometry coding category.
How many benchmarks do o1-mini and Qwen2-72B share?
21 benchmarks have published results for both models. o1-mini has 39 scored results on Noometry and Qwen2-72B has 26.