Model comparison
o1-mini vs Qwen2.5 72B Instruct
o1-mini is the stronger model overall, scoring 34.0 to 31.9 on the Noometry Index.
Last verified . 23 shared benchmarks.
Alibaba (Qwen)Summary
- They share 23 benchmarks with published results for both. o1-mini scores higher in 8 categories and Qwen2.5 72B Instruct in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where o1-mini leads 35.4 to 19.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 46.9% for o1-mini and 8.1% for Qwen2.5 72B Instruct.
- Qwen2.5 72B Instruct has downloadable open weights; the other is API-only.
Side by side
| o1-mini | Qwen2.5 72B Instruct | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 34.0 | 31.9 |
| Released | 2024-09-12 | 2024-09 |
| Weights | Proprietary | Open |
| Context window | — | 131K |
| Max output | — | 8K |
| Input $ / M tokens | — | $1.40 |
| Output $ / M tokens | — | $5.60 |
| Results tracked | 39 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o1-mini leads
o1-mini: 35.5 (#224), Qwen2.5 72B Instruct: 33.2 (#260)
| Benchmark | o1-mini | Qwen2.5 72B Instruct |
|---|---|---|
| WeirdML | 36.3% | 16% |
| LMArena Coding | 1362 | 1292 |
| Aider Polyglot | 32.9% | — |
| BigCodeBench Instruct | — | 45.8% |
| LiveBench Coding | 48% | — |
| BigCodeBench Complete | — | 55.9% |
| HumanEval+ | 89% | — |
| MBPP+ | 78.8% | — |
Agentic & Tool Use o1-mini leads
o1-mini: 24.6 (#118), Qwen2.5 72B Instruct: 22.1 (#133)
| Benchmark | o1-mini | Qwen2.5 72B Instruct |
|---|---|---|
| TheAgentCompany | — | 5.7% |
| Cybench | 10% | — |
| BALROG | — | 16.2% |
| METR Time Horizons | — | 35.8% |
Reasoning Qwen2.5 72B Instruct leads
o1-mini: 8.8 (#346), Qwen2.5 72B Instruct: 22.3 (#199)
| Benchmark | o1-mini | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1333 | 1271 |
| Epoch Capabilities Index | 135.82 | 129 |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 18.1% | — |
| ARC-AGI-1 | 14% | — |
| LiveBench Reasoning | 72.3% | — |
| DTBench | — | 62.9% |
| LiveBench Data Analysis | 57.9% | — |
| LMCA | — | 13.4% |
| BIG-Bench Hard | — | 79.8% |
| ForecastBench | — | 57.5 |
| HellaSwag | — | 84.8% |
| LiveBench | 57.8% | — |
| PIQA | — | 82.6% |
| WinoGrande | — | 82.3% |
Math o1-mini leads
o1-mini: 35.4 (#186), Qwen2.5 72B Instruct: 19.3 (#287)
| Benchmark | o1-mini | Qwen2.5 72B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 46.9% | 8.1% |
| LMArena Math | 1358 | 1283 |
| MATH Level 5 | 89.2% | 63.2% |
| Omni-MATH | — | 33% |
| LiveBench Math | 62% | — |
| FrontierMath (Feb 2025 set) | 1.7% | — |
Knowledge o1-mini leads
o1-mini: 34.9 (#192), Qwen2.5 72B Instruct: 27.0 (#253)
| Benchmark | o1-mini | Qwen2.5 72B Instruct |
|---|---|---|
| GPQA Diamond | 62.4% | 49.1% |
| Confabulations | 18.6% | 19.1% |
| LMArena Expert | 1316 | 1245 |
| MMLU-Pro | — | 63.1% |
| GPQA (HELM) | — | 42.6% |
| ARC (AI2) Challenge | — | 94.5% |
| MMLU | — | 85.3% |
| TriviaQA | — | 71.9% |
Multilingual o1-mini leads
o1-mini: 43.6 (#182), Qwen2.5 72B Instruct: 41.0 (#213)
| Benchmark | o1-mini | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 1289 | 1252 |
| LMArena Chinese | 1314 | 1272 |
| LMArena French | 1293 | 1280 |
| LMArena German | 1278 | 1234 |
| LMArena Japanese | 1245 | 1180 |
| LMArena Korean | 1223 | 1188 |
| LMArena Russian | 1283 | 1264 |
| LMArena Spanish | 1303 | 1256 |
Instruction Following o1-mini leads
o1-mini: 66.7 (#206), Qwen2.5 72B Instruct: 65.5 (#221)
| Benchmark | o1-mini | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 1304 | 1254 |
| LiveBench Instruction Following | 65.4% | — |
| IFEval | — | 80.6% |
Long Context o1-mini leads
o1-mini: 40.1 (#161), Qwen2.5 72B Instruct: 38.9 (#188)
| Benchmark | o1-mini | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1320 | 1282 |
Writing & Preference o1-mini leads
o1-mini: 48.4 (#202), Qwen2.5 72B Instruct: 46.7 (#215)
| Benchmark | o1-mini | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 1317 | 1269 |
| LMArena Creative Writing | 1244 | 1221 |
| LMArena Multi-Turn | 1314 | 1272 |
| Short-Story Creative Writing | 64.9% | — |
| WildBench | — | 80.2% |
| LiveBench Language | 40.9% | — |
Frequently asked questions
Is o1-mini better than Qwen2.5 72B Instruct?
o1-mini is the stronger model overall, scoring 34.0 to 31.9 on the Noometry Index.
Is o1-mini or Qwen2.5 72B Instruct better for coding?
o1-mini scores higher on coding benchmarks: 35.5 versus 33.2 in the Noometry coding category.
How many benchmarks do o1-mini and Qwen2.5 72B Instruct share?
23 benchmarks have published results for both models. o1-mini has 39 scored results on Noometry and Qwen2.5 72B Instruct has 43.