# Claude 3.7 Sonnet vs Qwen3.6 Plus

> Qwen3.6 Plus is the stronger model overall, scoring 47.5 to 39.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-7-sonnet-vs-qwen3-6-plus
- Last updated: 2026-10-12
- Shared benchmarks: 22

## Summary

- They share 22 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 1 category and Qwen3.6 Plus in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.6 Plus leads 56.1 to 39.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 57.8% for Claude 3.7 Sonnet and 93.3% for Qwen3.6 Plus.

## Snapshot

| | Claude 3.7 Sonnet | Qwen3.6 Plus |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 39.5 | 47.5 |
| Rank | 164 | 62 |
| Context | — | 1M |
| Input $/M | — | $0.50 |
| Output $/M | — | $3 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude 3.7 Sonnet: 40.6 (#136)
- Qwen3.6 Plus: 40.8 (#130)

| Benchmark | Claude 3.7 Sonnet | Qwen3.6 Plus |
|---|---|---|
| SWE-bench Verified | 61% | 57.9% |
| LMArena Coding | 1361 | 1467 |
| SWE-bench Verified (bash only) | 52.8% | — |
| Aider Polyglot | 64.9% | — |
| LMArena WebDev | — | 1461 |
| SciCode | — | 40.7% |
| GSO | 3.8% | — |
| LiveBench Coding | 74.5% | — |
| CadEval | 54% | — |
| ALE-Bench | — | 670.15 |

## Agentic & Tool Use

- Claude 3.7 Sonnet: 34.1 (#50)
- Qwen3.6 Plus: —

| Benchmark | Claude 3.7 Sonnet | Qwen3.6 Plus |
|---|---|---|
| TheAgentCompany | 30.9% | — |
| Cybench | 20% | — |
| DeepResearch Bench | 43.6% | — |
| OSWorld | 35.8% | — |
| METR Time Horizons | 60% | — |
| Vending-Bench 2 | — | 5,115 |

## Reasoning

- Claude 3.7 Sonnet: 18.6 (#277)
- Qwen3.6 Plus: 29.3 (#93)

| Benchmark | Claude 3.7 Sonnet | Qwen3.6 Plus |
|---|---|---|
| LMArena Hard Prompts | 1333 | 1449 |
| Epoch Capabilities Index | 141.16 | 147.65 |
| ARC-AGI-2 | 0.9% | — |
| SimpleBench | 46.4% | — |
| NYT Connections (extended) | — | 60.3% |
| ARC-AGI-1 | 28.6% | — |
| CritPt | — | 2.9% |
| Chess Puzzles | — | 17% |
| EnigmaEval | 4.2% | — |
| Thematic Generalization | — | 59.5% |
| LiveBench Reasoning | 87.8% | — |
| Mystery Game Puzzles | — | 12% |
| DTBench | — | 81.9% |
| LiveBench Data Analysis | 74% | — |
| LMCA | — | 33.1% |
| ForecastBench | 61.8 | — |
| LiveBench | 76.1% | — |

## Math

- Claude 3.7 Sonnet: 37.5 (#153)
- Qwen3.6 Plus: 51.8 (#54)

| Benchmark | Claude 3.7 Sonnet | Qwen3.6 Plus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 93.3% |
| LMArena Math | 1337 | 1450 |
| FrontierMath (Feb 2025 set) | 4.1% | 26.2% |
| FrontierMath (Tiers 1-3) | — | 38.2% |
| Omni-MATH | 33% | — |
| LiveBench Math | 79% | — |
| MATH Level 5 | 91.2% | — |
| FrontierMath Tier 4 (v1) | — | 8.3% |

## Knowledge

- Claude 3.7 Sonnet: 39.8 (#130)
- Qwen3.6 Plus: 56.1 (#45)

| Benchmark | Claude 3.7 Sonnet | Qwen3.6 Plus |
|---|---|---|
| GPQA Diamond | 79.7% | 88.4% |
| LMArena Expert | 1321 | 1454 |
| Humanity's Last Exam | 8% | — |
| SimpleQA Verified | — | 44.1% |
| MMLU-Pro | 78.4% | — |
| Confabulations | 14.7% | — |
| GPQA (HELM) | 60.8% | — |

## Multimodal

- Claude 3.7 Sonnet: 33.7 (#95)
- Qwen3.6 Plus: —

| Benchmark | Claude 3.7 Sonnet | Qwen3.6 Plus |
|---|---|---|
| LMArena Vision | 1169 | — |
| GeoBench | 68% | — |
| VPCT | 39% | — |
| SpatialViz-Bench | 33.9% | — |

## Multilingual

- Claude 3.7 Sonnet: 44.1 (#179)
- Qwen3.6 Plus: 53.3 (#70)

| Benchmark | Claude 3.7 Sonnet | Qwen3.6 Plus |
|---|---|---|
| LMArena Non-English | 1296 | 1424 |
| LMArena Chinese | 1299 | 1477 |
| LMArena French | 1303 | 1455 |
| LMArena German | 1301 | 1452 |
| LMArena Japanese | 1267 | 1389 |
| LMArena Korean | 1249 | 1379 |
| LMArena Russian | 1311 | 1434 |
| LMArena Spanish | 1298 | 1432 |

## Instruction Following

- Claude 3.7 Sonnet: 72.9 (#125)
- Qwen3.6 Plus: 75.0 (#74)

| Benchmark | Claude 3.7 Sonnet | Qwen3.6 Plus |
|---|---|---|
| LMArena Instruction Following | 1352 | 1425 |
| LiveBench Instruction Following | 81.3% | — |
| IFEval | 83.4% | — |

## Long Context

- Claude 3.7 Sonnet: 50.3 (#10)
- Qwen3.6 Plus: 45.2 (#49)

| Benchmark | Claude 3.7 Sonnet | Qwen3.6 Plus |
|---|---|---|
| LMArena Longer Query | 1373 | 1439 |
| Fiction.LiveBench | 83.3% | — |
| CL-bench | — | 20.3% |

## Writing & Preference

- Claude 3.7 Sonnet: 54.4 (#150)
- Qwen3.6 Plus: 62.2 (#82)

| Benchmark | Claude 3.7 Sonnet | Qwen3.6 Plus |
|---|---|---|
| LMArena Text | 1314 | 1437 |
| LMArena Creative Writing | 1332 | 1404 |
| LMArena Multi-Turn | 1339 | 1438 |
| 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 Qwen3.6 Plus?

Qwen3.6 Plus is the stronger model overall, scoring 47.5 to 39.5 on the Noometry Index.

### Is Claude 3.7 Sonnet or Qwen3.6 Plus better for coding?

They score almost the same on coding (40.6 vs 40.8); test both on your own repository before choosing.

### How many benchmarks do Claude 3.7 Sonnet and Qwen3.6 Plus share?

22 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and Qwen3.6 Plus has 37.