# o1-mini vs Qwen2.5 72B Instruct

> o1-mini is the stronger model overall, scoring 33.7 to 31.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/o1-mini-vs-qwen2-5-72b-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 23

## 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 33.7 to 18.1.
- 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.

## Snapshot

| | o1-mini | Qwen2.5 72B Instruct |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 33.7 | 31.5 |
| Rank | 230 | 259 |
| Context | — | 131K |
| Input $/M | — | $1.40 |
| Output $/M | — | $5.60 |
| Weights | Proprietary | Open |

## Coding

- o1-mini: 35.1 (#218)
- Qwen2.5 72B Instruct: 32.8 (#256)

| Benchmark | o1-mini | Qwen2.5 72B Instruct |
|---|---|---|
| WeirdML | 36.3% | 16% |
| LMArena Coding | 1362 | 1293 |
| 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: 24.3 (#112)
- Qwen2.5 72B Instruct: 22.0 (#124)

| Benchmark | o1-mini | Qwen2.5 72B Instruct |
|---|---|---|
| TheAgentCompany | — | 5.7% |
| Cybench | 10% | — |
| BALROG | — | 16.2% |
| METR Time Horizons | — | 35.8% |

## Reasoning

- o1-mini: 8.9 (#340)
- Qwen2.5 72B Instruct: 21.4 (#197)

| Benchmark | o1-mini | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1333 | 1271 |
| Epoch Capabilities Index | 135.82 | 129.01 |
| 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: 33.7 (#168)
- Qwen2.5 72B Instruct: 18.1 (#281)

| 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: 34.8 (#180)
- Qwen2.5 72B Instruct: 26.9 (#247)

| 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: 43.8 (#177)
- Qwen2.5 72B Instruct: 41.2 (#208)

| Benchmark | o1-mini | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 1289 | 1252 |
| LMArena Chinese | 1314 | 1272 |
| LMArena French | 1292 | 1279 |
| LMArena German | 1278 | 1234 |
| LMArena Japanese | 1245 | 1180 |
| LMArena Korean | 1223 | 1188 |
| LMArena Russian | 1283 | 1264 |
| LMArena Spanish | 1302 | 1255 |

## Instruction Following

- o1-mini: 67.0 (#200)
- Qwen2.5 72B Instruct: 65.7 (#216)

| Benchmark | o1-mini | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 1304 | 1254 |
| LiveBench Instruction Following | 65.4% | — |
| IFEval | — | 80.6% |

## Long Context

- o1-mini: 40.1 (#156)
- Qwen2.5 72B Instruct: 38.9 (#183)

| Benchmark | o1-mini | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1321 | 1282 |

## Writing & Preference

- o1-mini: 48.6 (#196)
- Qwen2.5 72B Instruct: 46.9 (#210)

| 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% | — |

## FAQ

### Is o1-mini better than Qwen2.5 72B Instruct?

o1-mini is the stronger model overall, scoring 33.7 to 31.5 on the Noometry Index.

### Is o1-mini or Qwen2.5 72B Instruct better for coding?

o1-mini scores higher on coding benchmarks: 35.1 versus 32.8 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.