# o1 vs Qwen2.5-Max

> o1 and Qwen2.5-Max score almost the same on the Noometry Index (40.9 vs 40.7), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/o1-vs-qwen2-5-max
- Last updated: 2026-10-10
- Shared benchmarks: 27

## Summary

- They share 27 benchmarks with published results for both. o1 scores higher in 7 categories and Qwen2.5-Max in 1 category; 5 gaps are clear of the uncertainty.
- The widest gap is in long context, where o1 leads 50.3 to 41.4.
- The biggest single-benchmark swing is LiveBench Reasoning: 91.6% for o1 and 51.4% for Qwen2.5-Max.

## Snapshot

| | o1 | Qwen2.5-Max |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 40.9 | 40.7 |
| Rank | 143 | 146 |
| Context | 200K | — |
| Input $/M | $15 | — |
| Output $/M | $60 | — |
| Weights | Proprietary | Proprietary |

## Coding

- o1: 46.1 (#70)
- Qwen2.5-Max: 41.8 (#117)

| Benchmark | o1 | Qwen2.5-Max |
|---|---|---|
| LiveBench Coding | 69.7% | 64.4% |
| LMArena Coding | 1367 | 1359 |
| Aider Polyglot | 61.7% | — |
| WeirdML | 47.6% | — |
| CadEval | 56% | — |
| HumanEval+ | 89% | — |
| MBPP+ | 80.2% | — |

## Agentic & Tool Use

- o1: 24.6 (#117)
- Qwen2.5-Max: —

| Benchmark | o1 | Qwen2.5-Max |
|---|---|---|
| Cybench | 10% | — |
| METR Time Horizons | 51.1% | — |

## Reasoning

- o1: 27.9 (#111)
- Qwen2.5-Max: 25.6 (#147)

| Benchmark | o1 | Qwen2.5-Max |
|---|---|---|
| LiveBench Reasoning | 91.6% | 51.4% |
| LMArena Hard Prompts | 1371 | 1360 |
| LiveBench Data Analysis | 65.5% | 67.9% |
| Epoch Capabilities Index | 141.91 | 132.53 |
| LiveBench | 75.7% | 62.3% |
| SimpleBench | 41.7% | — |
| ARC-AGI-1 | 30.7% | — |
| Chess Puzzles | 15% | — |
| EnigmaEval | 5.7% | — |
| DTBench | 74.7% | — |
| LMCA | 22.3% | — |

## Math

- o1: 36.1 (#175)
- Qwen2.5-Max: 36.9 (#162)

| Benchmark | o1 | Qwen2.5-Max |
|---|---|---|
| LiveBench Math | 80.3% | 58.4% |
| LMArena Math | 1388 | 1369 |
| FrontierMath (Tiers 1-3) | 14.7% | — |
| OTIS Mock AIME 2024-2025 | 73.3% | — |
| MATH Level 5 | 94.7% | — |
| FrontierMath (Feb 2025 set) | 9.3% | — |

## Knowledge

- o1: 41.5 (#110)
- Qwen2.5-Max: 35.3 (#186)

| Benchmark | o1 | Qwen2.5-Max |
|---|---|---|
| Confabulations | 11.7% | 21.8% |
| LMArena Expert | 1361 | 1337 |
| GPQA Diamond | 76.8% | — |
| Humanity's Last Exam | 8% | — |
| SimpleQA Verified | 41.1% | — |

## Multimodal

- o1: 34.2 (#93)
- Qwen2.5-Max: —

| Benchmark | o1 | Qwen2.5-Max |
|---|---|---|
| LMArena Vision | 1168 | — |
| GeoBench | 80% | — |
| VPCT | 37% | — |
| SpatialViz-Bench | 41.4% | — |

## Multilingual

- o1: 48.6 (#142)
- Qwen2.5-Max: 48.1 (#146)

| Benchmark | o1 | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | 1358 | 1352 |
| LMArena Chinese | 1394 | 1382 |
| LMArena French | 1344 | 1396 |
| LMArena German | 1337 | 1350 |
| LMArena Japanese | 1346 | 1300 |
| LMArena Korean | 1396 | 1304 |
| LMArena Russian | 1356 | 1353 |
| LMArena Spanish | 1345 | 1377 |

## Instruction Following

- o1: 74.8 (#86)
- Qwen2.5-Max: 71.3 (#152)

| Benchmark | o1 | Qwen2.5-Max |
|---|---|---|
| LiveBench Instruction Following | 81.5% | 75.3% |
| LMArena Instruction Following | 1367 | 1335 |

## Long Context

- o1: 50.3 (#9)
- Qwen2.5-Max: 41.4 (#142)

| Benchmark | o1 | Qwen2.5-Max |
|---|---|---|
| LMArena Longer Query | 1378 | 1358 |
| Fiction.LiveBench | 83.3% | — |

## Writing & Preference

- o1: 55.6 (#144)
- Qwen2.5-Max: 55.4 (#146)

| Benchmark | o1 | Qwen2.5-Max |
|---|---|---|
| LMArena Text | 1366 | 1367 |
| LMArena Creative Writing | 1348 | 1339 |
| Short-Story Creative Writing | 70.2% | 72.9% |
| LMArena Multi-Turn | 1369 | 1364 |
| LiveBench Language | 65.4% | 56.3% |

## FAQ

### Is o1 better than Qwen2.5-Max?

o1 and Qwen2.5-Max score almost the same on the Noometry Index (40.9 vs 40.7), so choose on price, context window or the category you care about most.

### Is o1 or Qwen2.5-Max better for coding?

o1 scores higher on coding benchmarks: 46.1 versus 41.8 in the Noometry coding category.

### How many benchmarks do o1 and Qwen2.5-Max share?

27 benchmarks have published results for both models. o1 has 52 scored results on Noometry and Qwen2.5-Max has 27.