# Claude Sonnet 5.5 vs Qwen3.7 Plus

> Claude Sonnet 5.5 is the stronger model overall, scoring 61.9 to 45.3 on the Noometry Index. Qwen3.7 Plus costs 5.7× less per token, which makes it the better buy when Claude Sonnet 5.5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/claude-sonnet-5-5-vs-qwen3-7-plus
- Last updated: 2026-10-12
- Shared benchmarks: 22

## Summary

- They share 22 benchmarks with published results for both. Claude Sonnet 5.5 scores higher in 10 categories and Qwen3.7 Plus in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 5.5 leads 87.9 to 50.5.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 88.8% for Claude Sonnet 5.5 and 34.4% for Qwen3.7 Plus.
- Qwen3.7 Plus is cheaper at $0.40 / $1.60 per million input/output tokens, against $2 / $10 for Claude Sonnet 5.5.

## Snapshot

| | Claude Sonnet 5.5 | Qwen3.7 Plus |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 61.9 | 45.3 |
| Rank | 10 | 72 |
| Context | 1M | 1M |
| Input $/M | $2 | $0.40 |
| Output $/M | $10 | $1.60 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Sonnet 5.5: 67.3 (#6)
- Qwen3.7 Plus: 36.6 (#206)

| Benchmark | Claude Sonnet 5.5 | Qwen3.7 Plus |
|---|---|---|
| FrontierCode | 52.1% | 10.2% |
| SciCode | 61% | 45.5% |
| LMArena Coding | 1513 | 1473 |
| CursorBench | 55.5% | — |
| LMArena WebDev | 1774 | — |
| FrontierSWE | 61.9% | — |
| ALE-Bench | 1,819 | — |

## Agentic & Tool Use

- Claude Sonnet 5.5: 45.0 (#16)
- Qwen3.7 Plus: 21.4 (#138)

| Benchmark | Claude Sonnet 5.5 | Qwen3.7 Plus |
|---|---|---|
| APEX-Agents | 75.5% | — |
| OSWorld 2.0 | — | 2.8% |

## Reasoning

- Claude Sonnet 5.5: 54.0 (#28)
- Qwen3.7 Plus: 39.3 (#59)

| Benchmark | Claude Sonnet 5.5 | Qwen3.7 Plus |
|---|---|---|
| NYT Connections (extended) | 80.5% | 74.8% |
| CritPt | 31.4% | 9.1% |
| LMArena Hard Prompts | 1495 | 1460 |
| Mystery Game Puzzles | 65% | 17% |
| Epoch Capabilities Index | 165.03 | 147.37 |
| Chess Puzzles | — | 24% |
| DTBench | — | 84% |
| LMCA | — | 37.6% |

## Math

- Claude Sonnet 5.5: 87.9 (#6)
- Qwen3.7 Plus: 50.5 (#56)

| Benchmark | Claude Sonnet 5.5 | Qwen3.7 Plus |
|---|---|---|
| FrontierMath (Tiers 1-3) | 88.8% | 34.4% |
| OTIS Mock AIME 2024-2025 | 100% | 93.3% |
| LMArena Math | 1510 | 1466 |
| FrontierMath Tier 4 | 80.5% | — |
| ProofBench | 100% | — |
| FrontierMath Erdős | 2.9% | — |

## Knowledge

- Claude Sonnet 5.5: 66.0 (#12)
- Qwen3.7 Plus: 54.9 (#51)

| Benchmark | Claude Sonnet 5.5 | Qwen3.7 Plus |
|---|---|---|
| GPQA Diamond | 95.6% | 87.9% |
| LMArena Expert | 1540 | 1467 |
| SimpleQA Verified | 46.5% | — |

## Multimodal

- Claude Sonnet 5.5: 51.5 (#6)
- Qwen3.7 Plus: 41.8 (#33)

| Benchmark | Claude Sonnet 5.5 | Qwen3.7 Plus |
|---|---|---|
| LMArena Vision | 1289 | 1279 |
| Furniture Assembly | 75% | — |
| LMArena Document | — | 1444 |

## Multilingual

- Claude Sonnet 5.5: 55.3 (#30)
- Qwen3.7 Plus: 54.8 (#38)

| Benchmark | Claude Sonnet 5.5 | Qwen3.7 Plus |
|---|---|---|
| LMArena Non-English | 1452 | 1445 |
| LMArena Chinese | 1522 | 1510 |
| LMArena Russian | 1451 | 1457 |
| LMArena French | — | 1473 |
| LMArena German | — | 1471 |
| LMArena Japanese | — | 1413 |
| LMArena Korean | — | 1415 |
| LMArena Spanish | — | 1457 |

## Instruction Following

- Claude Sonnet 5.5: 78.3 (#11)
- Qwen3.7 Plus: 75.8 (#52)

| Benchmark | Claude Sonnet 5.5 | Qwen3.7 Plus |
|---|---|---|
| LMArena Instruction Following | 1495 | 1440 |

## Long Context

- Claude Sonnet 5.5: 45.9 (#28)
- Qwen3.7 Plus: 44.5 (#65)

| Benchmark | Claude Sonnet 5.5 | Qwen3.7 Plus |
|---|---|---|
| LMArena Longer Query | 1498 | 1455 |

## Writing & Preference

- Claude Sonnet 5.5: 66.0 (#40)
- Qwen3.7 Plus: 64.3 (#56)

| Benchmark | Claude Sonnet 5.5 | Qwen3.7 Plus |
|---|---|---|
| LMArena Text | 1471 | 1455 |
| LMArena Creative Writing | 1465 | 1439 |
| LMArena Multi-Turn | 1474 | 1460 |

## FAQ

### Is Claude Sonnet 5.5 better than Qwen3.7 Plus?

Claude Sonnet 5.5 is the stronger model overall, scoring 61.9 to 45.3 on the Noometry Index. Qwen3.7 Plus costs 5.7× less per token, which makes it the better buy when Claude Sonnet 5.5's lead doesn't matter for your workload.

### Which is cheaper, Claude Sonnet 5.5 or Qwen3.7 Plus?

Qwen3.7 Plus is cheaper. It lists at $0.40 per million input tokens and $1.60 per million output tokens; Claude Sonnet 5.5 lists at $2 and $10.

### Is Claude Sonnet 5.5 or Qwen3.7 Plus better for coding?

Claude Sonnet 5.5 scores higher on coding benchmarks: 67.3 versus 36.6 in the Noometry coding category.

### Which has the bigger context window?

Both accept 1M tokens.

### How many benchmarks do Claude Sonnet 5.5 and Qwen3.7 Plus share?

22 benchmarks have published results for both models. Claude Sonnet 5.5 has 32 scored results on Noometry and Qwen3.7 Plus has 32.