# o3 vs Qwen Max

> o3 is the stronger model overall, scoring 47.4 to 34.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/o3-vs-qwen-max
- Last updated: 2026-10-10
- Shared benchmarks: 23

## Summary

- They share 23 benchmarks with published results for both. o3 scores higher in 8 categories and Qwen Max in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where o3 leads 48.9 to 21.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 84.4% for o3 and 16.1% for Qwen Max.
- Qwen Max is cheaper at $1.60 / $6.40 per million input/output tokens, against $2 / $8 for o3.
- o3 accepts more context: 200K tokens versus 33K.

## Snapshot

| | o3 | Qwen Max |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 47.4 | 34.4 |
| Rank | 53 | 226 |
| Context | 200K | 33K |
| Input $/M | $2 | $1.60 |
| Output $/M | $8 | $6.40 |
| Weights | Proprietary | Proprietary |

## Coding

- o3: 47.3 (#57)
- Qwen Max: 30.3 (#288)

| Benchmark | o3 | Qwen Max |
|---|---|---|
| Aider Polyglot | 81.3% | 21.8% |
| LMArena Coding | 1408 | 1288 |
| SWE-bench Verified | 62.3% | — |
| SWE-bench Verified (bash only) | 58.4% | — |
| GSO | 8.8% | — |
| WeirdML | 52.4% | — |
| CadEval | 74% | — |
| ALE-Bench | 933.55 | — |

## Agentic & Tool Use

- o3: 34.3 (#42)
- Qwen Max: —

| Benchmark | o3 | Qwen Max |
|---|---|---|
| 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)
- Qwen Max: 24.1 (#154)

| Benchmark | o3 | Qwen Max |
|---|---|---|
| LMArena Hard Prompts | 1402 | 1270 |
| 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)
- Qwen Max: 21.0 (#272)

| Benchmark | o3 | Qwen Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 84.4% | 16.1% |
| LMArena Math | 1426 | 1275 |
| MATH Level 5 | 97.8% | 67.2% |
| FrontierMath (Feb 2025 set) | 18.7% | 1% |
| FrontierMath (Tiers 1-3) | 33.3% | — |
| Omni-MATH | 71.4% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |

## Knowledge

- o3: 54.5 (#47)
- Qwen Max: 30.3 (#222)

| Benchmark | o3 | Qwen Max |
|---|---|---|
| GPQA Diamond | 81.8% | 56.1% |
| LMArena Expert | 1403 | 1248 |
| 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)
- Qwen Max: —

| Benchmark | o3 | Qwen Max |
|---|---|---|
| LMArena Vision | 1214 | — |
| GeoBench | 74% | — |
| VPCT | 52% | — |

## Multilingual

- o3: 51.9 (#99)
- Qwen Max: 42.0 (#197)

| Benchmark | o3 | Qwen Max |
|---|---|---|
| LMArena Non-English | 1402 | 1263 |
| LMArena Chinese | 1438 | 1254 |
| LMArena French | 1430 | 1329 |
| LMArena German | 1420 | 1254 |
| LMArena Japanese | 1404 | 1205 |
| LMArena Korean | 1371 | 1141 |
| LMArena Russian | 1407 | 1274 |
| LMArena Spanish | 1395 | 1290 |

## Instruction Following

- o3: 73.0 (#122)
- Qwen Max: 66.7 (#203)

| Benchmark | o3 | Qwen Max |
|---|---|---|
| LMArena Instruction Following | 1368 | 1262 |
| IFEval | 86.9% | — |

## Long Context

- o3: 53.2 (#6)
- Qwen Max: 39.4 (#175)

| Benchmark | o3 | Qwen Max |
|---|---|---|
| Fiction.LiveBench | 88.9% | 66.7% |
| LMArena Longer Query | 1372 | 1289 |
| CL-bench | 17.8% | — |

## Writing & Preference

- o3: 63.7 (#62)
- Qwen Max: 48.0 (#200)

| Benchmark | o3 | Qwen Max |
|---|---|---|
| LMArena Text | 1410 | 1282 |
| LMArena Creative Writing | 1359 | 1248 |
| LMArena Multi-Turn | 1405 | 1277 |
| Short-Story Creative Writing | 83.9% | — |
| EQ-Bench Creative Writing | 1676 | — |
| WildBench | 86.1% | — |

## FAQ

### Is o3 better than Qwen Max?

o3 is the stronger model overall, scoring 47.4 to 34.4 on the Noometry Index.

### Which is cheaper, o3 or Qwen Max?

Qwen Max is cheaper. It lists at $1.60 per million input tokens and $6.40 per million output tokens; o3 lists at $2 and $8.

### Is o3 or Qwen Max better for coding?

o3 scores higher on coding benchmarks: 47.3 versus 30.3 in the Noometry coding category.

### Which has the bigger context window?

o3 does, with 200K tokens against 33K.

### How many benchmarks do o3 and Qwen Max share?

23 benchmarks have published results for both models. o3 has 63 scored results on Noometry and Qwen Max has 23.