# Claude 3.7 Sonnet vs Claude Opus 5.5

> Claude Opus 5.5 is the stronger model overall, scoring 68.6 to 39.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-7-sonnet-vs-claude-opus-5-5
- Last updated: 2026-10-10
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 1 category and Claude Opus 5.5 in 9 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Opus 5.5 leads 80.2 to 18.6.
- The biggest single-benchmark swing is ARC-AGI-2: 0.9% for Claude 3.7 Sonnet and 93.3% for Claude Opus 5.5.

## Snapshot

| | Claude 3.7 Sonnet | Claude Opus 5.5 |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Noometry Index | 39.5 | 68.6 |
| Rank | 164 | 3 |
| Context | — | 1M |
| Input $/M | — | $4 |
| Output $/M | — | $20 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude 3.7 Sonnet: 40.6 (#136)
- Claude Opus 5.5: 71.9 (#3)

| Benchmark | Claude 3.7 Sonnet | Claude Opus 5.5 |
|---|---|---|
| LMArena Coding | 1361 | 1547 |
| SWE-bench Verified | 61% | — |
| FrontierCode | — | 54.6% |
| SWE-bench Verified (bash only) | 52.8% | — |
| Aider Polyglot | 64.9% | — |
| CursorBench | — | 57.8% |
| LMArena WebDev | — | 1813 |
| FrontierSWE | — | 62.3% |
| SciCode | — | 66.9% |
| GSO | 3.8% | — |
| LiveBench Coding | 74.5% | — |
| MirrorCode | — | 77.4% |
| CadEval | 54% | — |
| ALE-Bench | — | 2,147 |

## Agentic & Tool Use

- Claude 3.7 Sonnet: 34.1 (#50)
- Claude Opus 5.5: 45.3 (#15)

| Benchmark | Claude 3.7 Sonnet | Claude Opus 5.5 |
|---|---|---|
| APEX-Agents | — | 73.5% |
| TheAgentCompany | 30.9% | — |
| Cybench | 20% | — |
| DeepResearch Bench | 43.6% | — |
| OSWorld | 35.8% | — |
| GDP.pdf | — | 30.6% |
| METR Time Horizons | 60% | — |
| Vending-Bench 2 | — | 9,235 |

## Reasoning

- Claude 3.7 Sonnet: 18.6 (#277)
- Claude Opus 5.5: 80.2 (#3)

| Benchmark | Claude 3.7 Sonnet | Claude Opus 5.5 |
|---|---|---|
| ARC-AGI-2 | 0.9% | 93.3% |
| ARC-AGI-1 | 28.6% | 98.5% |
| LMArena Hard Prompts | 1333 | 1535 |
| Epoch Capabilities Index | 141.16 | 167.33 |
| SimpleBench | 46.4% | — |
| NYT Connections (extended) | — | 88.5% |
| CritPt | — | 31.7% |
| EnigmaEval | 4.2% | — |
| EBR-Bench | — | 71.4% |
| LiveBench Reasoning | 87.8% | — |
| Mystery Game Puzzles | — | 71% |
| DTBench | — | 98.9% |
| LiveBench Data Analysis | 74% | — |
| LMCA | — | 68.2% |
| ForecastBench | 61.8 | — |
| LiveBench | 76.1% | — |

## Math

- Claude 3.7 Sonnet: 37.5 (#153)
- Claude Opus 5.5: 91.8 (#3)

| Benchmark | Claude 3.7 Sonnet | Claude Opus 5.5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 100% |
| LMArena Math | 1337 | 1506 |
| FrontierMath (Tiers 1-3) | — | 91.2% |
| FrontierMath Tier 4 | — | 95% |
| ProofBench | — | 100% |
| Omni-MATH | 33% | — |
| LiveBench Math | 79% | — |
| MATH Level 5 | 91.2% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
| FrontierMath Erdős | — | 2.9% |

## Knowledge

- Claude 3.7 Sonnet: 39.8 (#130)
- Claude Opus 5.5: 66.4 (#10)

| Benchmark | Claude 3.7 Sonnet | Claude Opus 5.5 |
|---|---|---|
| GPQA Diamond | 79.7% | 90.6% |
| LMArena Expert | 1321 | 1547 |
| Humanity's Last Exam | 8% | — |
| SimpleQA Verified | — | 72.2% |
| MMLU-Pro | 78.4% | — |
| Confabulations | 14.7% | — |
| GPQA (HELM) | 60.8% | — |

## Multimodal

- Claude 3.7 Sonnet: 33.7 (#95)
- Claude Opus 5.5: 57.8 (#1)

| Benchmark | Claude 3.7 Sonnet | Claude Opus 5.5 |
|---|---|---|
| LMArena Vision | 1169 | 1321 |
| GeoBench | 68% | — |
| VPCT | 39% | — |
| Blueprint-Bench 2 | — | 51.2% |
| Furniture Assembly | — | 83.3% |
| SpatialViz-Bench | 33.9% | — |

## Multilingual

- Claude 3.7 Sonnet: 44.1 (#179)
- Claude Opus 5.5: 59.1 (#2)

| Benchmark | Claude 3.7 Sonnet | Claude Opus 5.5 |
|---|---|---|
| LMArena Non-English | 1296 | 1507 |
| LMArena Chinese | 1299 | 1588 |
| LMArena French | 1303 | 1514 |
| LMArena Russian | 1311 | 1520 |
| LMArena Spanish | 1298 | 1507 |
| LMArena German | 1301 | — |
| LMArena Japanese | 1267 | — |
| LMArena Korean | 1249 | — |

## Instruction Following

- Claude 3.7 Sonnet: 72.9 (#125)
- Claude Opus 5.5: 80.0 (#3)

| Benchmark | Claude 3.7 Sonnet | Claude Opus 5.5 |
|---|---|---|
| LMArena Instruction Following | 1352 | 1537 |
| LiveBench Instruction Following | 81.3% | — |
| IFEval | 83.4% | — |

## Long Context

- Claude 3.7 Sonnet: 50.3 (#10)
- Claude Opus 5.5: 47.1 (#19)

| Benchmark | Claude 3.7 Sonnet | Claude Opus 5.5 |
|---|---|---|
| LMArena Longer Query | 1373 | 1532 |
| Fiction.LiveBench | 83.3% | — |

## Writing & Preference

- Claude 3.7 Sonnet: 54.4 (#150)
- Claude Opus 5.5: 78.2 (#3)

| Benchmark | Claude 3.7 Sonnet | Claude Opus 5.5 |
|---|---|---|
| LMArena Text | 1314 | 1515 |
| LMArena Creative Writing | 1332 | 1533 |
| EQ-Bench Creative Writing | 1412 | 2050 |
| LMArena Multi-Turn | 1339 | 1499 |
| Short-Story Creative Writing | 81.1% | — |
| WildBench | 81.4% | — |
| LiveBench Language | 59.9% | — |

## FAQ

### Is Claude 3.7 Sonnet better than Claude Opus 5.5?

Claude Opus 5.5 is the stronger model overall, scoring 68.6 to 39.5 on the Noometry Index.

### Is Claude 3.7 Sonnet or Claude Opus 5.5 better for coding?

Claude Opus 5.5 scores higher on coding benchmarks: 71.9 versus 40.6 in the Noometry coding category.

### How many benchmarks do Claude 3.7 Sonnet and Claude Opus 5.5 share?

21 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and Claude Opus 5.5 has 44.