# Claude 3.7 Sonnet vs Qwen3 Max

> Qwen3 Max is the stronger model overall, scoring 43.5 to 39.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-7-sonnet-vs-qwen3-max
- Last updated: 2026-10-10
- Shared benchmarks: 22

## Summary

- They share 22 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 1 category and Qwen3 Max in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Qwen3 Max leads 53.9 to 44.3.
- The biggest single-benchmark swing is Fiction.LiveBench: 83.3% for Claude 3.7 Sonnet and 66.7% for Qwen3 Max.

## Snapshot

| | Claude 3.7 Sonnet | Qwen3 Max |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 39.4 | 43.5 |
| Rank | 154 | 82 |
| Context | — | 262K |
| Input $/M | — | $1.20 |
| Output $/M | — | $6 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude 3.7 Sonnet: 41.1 (#120)
- Qwen3 Max: 42.4 (#93)

| Benchmark | Claude 3.7 Sonnet | Qwen3 Max |
|---|---|---|
| LMArena Coding | 1361 | 1456 |
| SWE-bench Verified | 61% | — |
| SWE-bench Verified (bash only) | 52.8% | — |
| Aider Polyglot | 64.9% | — |
| GSO | 3.8% | — |
| LiveBench Coding | 74.5% | — |
| CadEval | 54% | — |
| ALE-Bench | — | 370.45 |

## Agentic & Tool Use

- Claude 3.7 Sonnet: 33.9 (#46)
- Qwen3 Max: —

| Benchmark | Claude 3.7 Sonnet | Qwen3 Max |
|---|---|---|
| TheAgentCompany | 30.9% | — |
| Cybench | 20% | — |
| DeepResearch Bench | 43.6% | — |
| OSWorld | 35.8% | — |
| METR Time Horizons | 60% | — |
| Vending-Bench 2 | — | 71.56 |

## Reasoning

- Claude 3.7 Sonnet: 18.7 (#252)
- Qwen3 Max: 22.0 (#186)

| Benchmark | Claude 3.7 Sonnet | Qwen3 Max |
|---|---|---|
| LMArena Hard Prompts | 1333 | 1448 |
| Epoch Capabilities Index | 141.16 | 142.41 |
| ARC-AGI-2 | 0.9% | — |
| SimpleBench | 46.4% | — |
| Kagi LLM Benchmark | — | 72.5% |
| NYT Connections (extended) | — | 30.1% |
| ARC-AGI-1 | 28.6% | — |
| Chess Puzzles | — | 4% |
| EnigmaEval | 4.2% | — |
| LiveBench Reasoning | 87.8% | — |
| Mystery Game Puzzles | — | 5% |
| DTBench | — | 82.1% |
| LiveBench Data Analysis | 74% | — |
| LMCA | — | 28.3% |
| ForecastBench | 61.8 | — |
| LiveBench | 76.1% | — |

## Math

- Claude 3.7 Sonnet: 35.7 (#137)
- Qwen3 Max: 37.6 (#94)

| Benchmark | Claude 3.7 Sonnet | Qwen3 Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 73.3% |
| LMArena Math | 1336 | 1447 |
| MATH Level 5 | 91.2% | 97.1% |
| FrontierMath (Tiers 1-3) | — | 18.9% |
| Omni-MATH | 33% | — |
| LiveBench Math | 79% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |

## Knowledge

- Claude 3.7 Sonnet: 39.7 (#117)
- Qwen3 Max: 48.1 (#72)

| Benchmark | Claude 3.7 Sonnet | Qwen3 Max |
|---|---|---|
| GPQA Diamond | 79.7% | 72.6% |
| LMArena Expert | 1321 | 1457 |
| Humanity's Last Exam | 8% | — |
| SimpleQA Verified | — | 48.7% |
| MMLU-Pro | 78.4% | — |
| Confabulations | 14.7% | — |
| GPQA (HELM) | 60.8% | — |

## Multimodal

- Claude 3.7 Sonnet: 33.1 (#90)
- Qwen3 Max: —

| Benchmark | Claude 3.7 Sonnet | Qwen3 Max |
|---|---|---|
| LMArena Vision | 1169 | — |
| GeoBench | 68% | — |
| VPCT | 39% | — |
| SpatialViz-Bench | 33.9% | — |

## Multilingual

- Claude 3.7 Sonnet: 44.3 (#174)
- Qwen3 Max: 53.9 (#58)

| Benchmark | Claude 3.7 Sonnet | Qwen3 Max |
|---|---|---|
| LMArena Non-English | 1296 | 1429 |
| LMArena Chinese | 1299 | 1479 |
| LMArena French | 1302 | 1450 |
| LMArena German | 1301 | 1463 |
| LMArena Japanese | 1268 | 1399 |
| LMArena Korean | 1249 | 1397 |
| LMArena Russian | 1311 | 1428 |
| LMArena Spanish | 1299 | 1463 |

## Instruction Following

- Claude 3.7 Sonnet: 73.1 (#120)
- Qwen3 Max: 75.0 (#81)

| Benchmark | Claude 3.7 Sonnet | Qwen3 Max |
|---|---|---|
| LMArena Instruction Following | 1352 | 1420 |
| LiveBench Instruction Following | 81.3% | — |
| IFEval | 83.4% | — |

## Long Context

- Claude 3.7 Sonnet: 50.2 (#10)
- Qwen3 Max: 41.6 (#129)

| Benchmark | Claude 3.7 Sonnet | Qwen3 Max |
|---|---|---|
| Fiction.LiveBench | 83.3% | 66.7% |
| LMArena Longer Query | 1373 | 1439 |
| CL-bench | — | 14.5% |

## Writing & Preference

- Claude 3.7 Sonnet: 54.6 (#145)
- Qwen3 Max: 62.6 (#72)

| Benchmark | Claude 3.7 Sonnet | Qwen3 Max |
|---|---|---|
| LMArena Text | 1314 | 1439 |
| LMArena Creative Writing | 1332 | 1401 |
| LMArena Multi-Turn | 1339 | 1446 |
| Short-Story Creative Writing | 81.1% | — |
| EQ-Bench Creative Writing | 1412 | — |
| WildBench | 81.4% | — |
| LiveBench Language | 59.9% | — |

## FAQ

### Is Claude 3.7 Sonnet better than Qwen3 Max?

Qwen3 Max is the stronger model overall, scoring 43.5 to 39.4 on the Noometry Index.

### Is Claude 3.7 Sonnet or Qwen3 Max better for coding?

Qwen3 Max scores higher on coding benchmarks: 42.4 versus 41.1 in the Noometry coding category.

### How many benchmarks do Claude 3.7 Sonnet and Qwen3 Max share?

22 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and Qwen3 Max has 33.