# o3 vs Qwen3.7 Max

> Qwen3.7 Max is the stronger model overall, scoring 51.4 to 47.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/o3-vs-qwen3-7-max
- Last updated: 2026-10-10
- Shared benchmarks: 25

## Summary

- They share 25 benchmarks with published results for both. o3 scores higher in 2 categories and Qwen3.7 Max in 7 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.7 Max leads 48.4 to 32.1.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 33.3% for o3 and 64.6% for Qwen3.7 Max.
- o3 is cheaper at $2 / $8 per million input/output tokens, against $2.50 / $7.50 for Qwen3.7 Max.
- Qwen3.7 Max accepts more context: 1M tokens versus 200K.

## Snapshot

| | o3 | Qwen3.7 Max |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 47.4 | 51.4 |
| Rank | 53 | 35 |
| Context | 200K | 1M |
| Input $/M | $2 | $2.50 |
| Output $/M | $8 | $7.50 |
| Weights | Proprietary | Proprietary |

## Coding

- o3: 47.3 (#57)
- Qwen3.7 Max: 50.2 (#43)

| Benchmark | o3 | Qwen3.7 Max |
|---|---|---|
| SWE-bench Verified | 62.3% | 77.3% |
| LMArena Coding | 1408 | 1498 |
| ALE-Bench | 933.55 | 1,189 |
| SWE-bench Verified (bash only) | 58.4% | — |
| Aider Polyglot | 81.3% | — |
| LMArena WebDev | — | 1515 |
| SciCode | — | 48.8% |
| GSO | 8.8% | — |
| WeirdML | 52.4% | — |
| CadEval | 74% | — |

## Agentic & Tool Use

- o3: 34.3 (#42)
- Qwen3.7 Max: 21.8 (#129)

| Benchmark | o3 | Qwen3.7 Max |
|---|---|---|
| Berkeley Function Calling Leaderboard | 63% | — |
| GDPval | 30.8% | — |
| DeepResearch Bench | 45.2% | — |
| OSWorld | 23% | — |
| GBAEval | — | 0.4% |
| LMArena Search | 1144 | — |
| METR Time Horizons | 65.4% | — |

## Reasoning

- o3: 32.1 (#66)
- Qwen3.7 Max: 48.4 (#36)

| Benchmark | o3 | Qwen3.7 Max |
|---|---|---|
| SimpleBench | 53.1% | 70.4% |
| CritPt | 1.4% | 13.4% |
| Chess Puzzles | 38% | 19% |
| LMArena Hard Prompts | 1402 | 1483 |
| Mystery Game Puzzles | 29% | 32% |
| DTBench | 84.8% | 92.3% |
| LMCA | 39.7% | 44% |
| Epoch Capabilities Index | 146.88 | 153.74 |
| ARC-AGI-2 | 6.5% | — |
| Kagi LLM Benchmark | 67.6% | — |
| NYT Connections (extended) | — | 85.1% |
| ARC-AGI-1 | 60.8% | — |
| EnigmaEval | 13.1% | — |
| EBR-Bench | — | 9.5% |
| ForecastBench | 62.5 | — |

## Math

- o3: 48.9 (#49)
- Qwen3.7 Max: 62.3 (#26)

| Benchmark | o3 | Qwen3.7 Max |
|---|---|---|
| FrontierMath (Tiers 1-3) | 33.3% | 64.6% |
| OTIS Mock AIME 2024-2025 | 84.4% | 95.6% |
| LMArena Math | 1426 | 1488 |
| FrontierMath Tier 4 | — | 34.1% |
| ProofBench | — | 26% |
| 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)
- Qwen3.7 Max: 61.7 (#24)

| Benchmark | o3 | Qwen3.7 Max |
|---|---|---|
| GPQA Diamond | 81.8% | 90.9% |
| SimpleQA Verified | 49.4% | 55.8% |
| LMArena Expert | 1403 | 1488 |
| Humanity's Last Exam | 20.3% | — |
| MMLU-Pro | 85.9% | — |
| Confabulations | 14.4% | — |
| GPQA (HELM) | 75.3% | — |

## Multimodal

- o3: 40.7 (#35)
- Qwen3.7 Max: —

| Benchmark | o3 | Qwen3.7 Max |
|---|---|---|
| LMArena Vision | 1214 | — |
| GeoBench | 74% | — |
| VPCT | 52% | — |

## Multilingual

- o3: 51.9 (#99)
- Qwen3.7 Max: 57.1 (#13)

| Benchmark | o3 | Qwen3.7 Max |
|---|---|---|
| LMArena Non-English | 1402 | 1475 |
| LMArena Chinese | 1438 | 1533 |
| LMArena Russian | 1407 | 1482 |
| LMArena French | 1430 | — |
| LMArena German | 1420 | — |
| LMArena Japanese | 1404 | — |
| LMArena Korean | 1371 | — |
| LMArena Spanish | 1395 | — |

## Instruction Following

- o3: 73.0 (#122)
- Qwen3.7 Max: 76.9 (#34)

| Benchmark | o3 | Qwen3.7 Max |
|---|---|---|
| LMArena Instruction Following | 1368 | 1460 |
| IFEval | 86.9% | — |

## Long Context

- o3: 53.2 (#6)
- Qwen3.7 Max: 45.4 (#34)

| Benchmark | o3 | Qwen3.7 Max |
|---|---|---|
| LMArena Longer Query | 1372 | 1484 |
| Fiction.LiveBench | 88.9% | — |
| CL-bench | 17.8% | — |

## Writing & Preference

- o3: 63.7 (#62)
- Qwen3.7 Max: 65.2 (#52)

| Benchmark | o3 | Qwen3.7 Max |
|---|---|---|
| LMArena Text | 1410 | 1476 |
| LMArena Creative Writing | 1359 | 1450 |
| LMArena Multi-Turn | 1405 | 1482 |
| Short-Story Creative Writing | 83.9% | — |
| EQ-Bench Creative Writing | 1676 | — |
| WildBench | 86.1% | — |
| EQ-Bench 4 | — | 1110 |

## FAQ

### Is o3 better than Qwen3.7 Max?

Qwen3.7 Max is the stronger model overall, scoring 51.4 to 47.4 on the Noometry Index.

### Which is cheaper, o3 or Qwen3.7 Max?

o3 is cheaper. It lists at $2 per million input tokens and $8 per million output tokens; Qwen3.7 Max lists at $2.50 and $7.50.

### Is o3 or Qwen3.7 Max better for coding?

Qwen3.7 Max scores higher on coding benchmarks: 50.2 versus 47.3 in the Noometry coding category.

### Which has the bigger context window?

Qwen3.7 Max does, with 1M tokens against 200K.

### How many benchmarks do o3 and Qwen3.7 Max share?

25 benchmarks have published results for both models. o3 has 63 scored results on Noometry and Qwen3.7 Max has 33.