# o3 vs Qwen3.5 Max Preview

> o3 is the stronger model overall, scoring 47.4 to 44.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/o3-vs-qwen3-5-max-preview
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. o3 scores higher in 5 categories and Qwen3.5 Max Preview in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where o3 leads 54.5 to 41.1.

## Snapshot

| | o3 | Qwen3.5 Max Preview |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 47.4 | 44.7 |
| Rank | 53 | 72 |
| Context | 200K | — |
| Input $/M | $2 | — |
| Output $/M | $8 | — |
| Weights | Proprietary | Proprietary |

## Coding

- o3: 47.3 (#57)
- Qwen3.5 Max Preview: 43.4 (#79)

| Benchmark | o3 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Coding | 1408 | 1488 |
| SWE-bench Verified | 62.3% | — |
| SWE-bench Verified (bash only) | 58.4% | — |
| Aider Polyglot | 81.3% | — |
| GSO | 8.8% | — |
| WeirdML | 52.4% | — |
| CadEval | 74% | — |
| ALE-Bench | 933.55 | — |

## Agentic & Tool Use

- o3: 34.3 (#42)
- Qwen3.5 Max Preview: —

| Benchmark | o3 | Qwen3.5 Max Preview |
|---|---|---|
| Berkeley Function Calling Leaderboard | 63% | — |
| GDPval | 30.8% | — |
| DeepResearch Bench | 45.2% | — |
| OSWorld | 23% | — |
| LMArena Search | 1144 | — |
| METR Time Horizons | 65.4% | — |

## Reasoning

- o3: 32.1 (#66)
- Qwen3.5 Max Preview: 29.6 (#81)

| Benchmark | o3 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Hard Prompts | 1402 | 1483 |
| ARC-AGI-2 | 6.5% | — |
| SimpleBench | 53.1% | — |
| Kagi LLM Benchmark | 67.6% | — |
| ARC-AGI-1 | 60.8% | — |
| CritPt | 1.4% | — |
| Chess Puzzles | 38% | — |
| EnigmaEval | 13.1% | — |
| Mystery Game Puzzles | 29% | — |
| DTBench | 84.8% | — |
| LMCA | 39.7% | — |
| Epoch Capabilities Index | 146.88 | — |
| ForecastBench | 62.5 | — |

## Math

- o3: 48.9 (#49)
- Qwen3.5 Max Preview: 37.3 (#99)

| Benchmark | o3 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Math | 1426 | 1473 |
| FrontierMath (Tiers 1-3) | 33.3% | — |
| OTIS Mock AIME 2024-2025 | 84.4% | — |
| Omni-MATH | 71.4% | — |
| MATH Level 5 | 97.8% | — |
| FrontierMath (Feb 2025 set) | 18.7% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |

## Knowledge

- o3: 54.5 (#47)
- Qwen3.5 Max Preview: 41.1 (#104)

| Benchmark | o3 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Expert | 1403 | 1489 |
| GPQA Diamond | 81.8% | — |
| Humanity's Last Exam | 20.3% | — |
| SimpleQA Verified | 49.4% | — |
| MMLU-Pro | 85.9% | — |
| Confabulations | 14.4% | — |
| GPQA (HELM) | 75.3% | — |

## Multimodal

- o3: 40.7 (#35)
- Qwen3.5 Max Preview: —

| Benchmark | o3 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Vision | 1214 | — |
| GeoBench | 74% | — |
| VPCT | 52% | — |

## Multilingual

- o3: 51.9 (#99)
- Qwen3.5 Max Preview: 56.4 (#21)

| Benchmark | o3 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Non-English | 1402 | 1465 |
| LMArena Chinese | 1438 | 1534 |
| LMArena French | 1430 | 1483 |
| LMArena German | 1420 | 1487 |
| LMArena Japanese | 1404 | 1497 |
| LMArena Korean | 1371 | 1438 |
| LMArena Russian | 1407 | 1472 |
| LMArena Spanish | 1395 | 1470 |

## Instruction Following

- o3: 73.0 (#122)
- Qwen3.5 Max Preview: 77.2 (#28)

| Benchmark | o3 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Instruction Following | 1368 | 1467 |
| IFEval | 86.9% | — |

## Long Context

- o3: 53.2 (#6)
- Qwen3.5 Max Preview: 45.2 (#44)

| Benchmark | o3 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Longer Query | 1372 | 1477 |
| Fiction.LiveBench | 88.9% | — |
| CL-bench | 17.8% | — |

## Writing & Preference

- o3: 63.7 (#62)
- Qwen3.5 Max Preview: 66.1 (#39)

| Benchmark | o3 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Text | 1410 | 1471 |
| LMArena Creative Writing | 1359 | 1464 |
| LMArena Multi-Turn | 1405 | 1478 |
| Short-Story Creative Writing | 83.9% | — |
| EQ-Bench Creative Writing | 1676 | — |
| WildBench | 86.1% | — |

## FAQ

### Is o3 better than Qwen3.5 Max Preview?

o3 is the stronger model overall, scoring 47.4 to 44.7 on the Noometry Index.

### Is o3 or Qwen3.5 Max Preview better for coding?

o3 scores higher on coding benchmarks: 47.3 versus 43.4 in the Noometry coding category.

### How many benchmarks do o3 and Qwen3.5 Max Preview share?

17 benchmarks have published results for both models. o3 has 63 scored results on Noometry and Qwen3.5 Max Preview has 17.