# Claude Opus 5.5 vs Claude Sonnet 4

> Claude Opus 5.5 is the stronger model overall, scoring 68.5 to 40.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-opus-5-5-vs-claude-sonnet-4
- Last updated: 2026-10-10
- Shared benchmarks: 20

## Summary

- They share 20 benchmarks with published results for both. Claude Opus 5.5 scores higher in 10 categories and Claude Sonnet 4 in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Opus 5.5 leads 79.5 to 23.0.
- The biggest single-benchmark swing is ARC-AGI-2: 92.5% for Claude Opus 5.5 and 5.9% for Claude Sonnet 4.
- Claude Sonnet 4 is cheaper at $3 / $15 per million input/output tokens, against $4 / $20 for Claude Opus 5.5.
- Claude Opus 5.5 accepts more context: 1M tokens versus 200K.

## Snapshot

| | Claude Opus 5.5 | Claude Sonnet 4 |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Noometry Index | 68.5 | 40.6 |
| Rank | 3 | 139 |
| Context | 1M | 200K |
| Input $/M | $4 | $3 |
| Output $/M | $20 | $15 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Opus 5.5: 71.4 (#1)
- Claude Sonnet 4: 44.0 (#70)

| Benchmark | Claude Opus 5.5 | Claude Sonnet 4 |
|---|---|---|
| SciCode | 66.9% | 40% |
| LMArena Coding | 1545 | 1414 |
| FrontierCode | 54.4% | — |
| SWE-bench Verified (bash only) | — | 64.9% |
| Aider Polyglot | — | 61.3% |
| CursorBench | 57.8% | — |
| LMArena WebDev | 1820 | — |
| FrontierSWE | 62.3% | — |
| GSO | — | 4.9% |
| WeirdML | — | 46.1% |
| MirrorCode | 77.4% | — |
| ALE-Bench | — | 655.35 |

## Agentic & Tool Use

- Claude Opus 5.5: 45.3 (#13)
- Claude Sonnet 4: 38.3 (#29)

| Benchmark | Claude Opus 5.5 | Claude Sonnet 4 |
|---|---|---|
| APEX-Agents | 73.5% | — |
| TheAgentCompany | — | 33.1% |
| Cybench | — | 35% |
| DeepResearch Bench | — | 46.6% |
| OSWorld | — | 43.9% |
| GDP.pdf | 30.6% | — |
| METR Time Horizons | — | 62% |

## Reasoning

- Claude Opus 5.5: 79.5 (#2)
- Claude Sonnet 4: 23.0 (#169)

| Benchmark | Claude Opus 5.5 | Claude Sonnet 4 |
|---|---|---|
| ARC-AGI-2 | 92.5% | 5.9% |
| ARC-AGI-1 | 97.5% | 40% |
| CritPt | 31.7% | 0.3% |
| LMArena Hard Prompts | 1545 | 1372 |
| DTBench | 98.9% | 77.1% |
| LMCA | 68.2% | 29% |
| SimpleBench | — | 45.5% |
| Kagi LLM Benchmark | — | 73% |
| NYT Connections (extended) | 88.5% | — |
| EnigmaEval | — | 3.1% |
| EBR-Bench | 71.4% | — |
| Mystery Game Puzzles | 71% | — |
| Epoch Capabilities Index | — | 141.69 |
| ForecastBench | — | 60.2 |

## Math

- Claude Opus 5.5: 92.4 (#2)
- Claude Sonnet 4: 41.5 (#71)

| Benchmark | Claude Opus 5.5 | Claude Sonnet 4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 100% | 71.1% |
| FrontierMath (Tiers 1-3) | 91.2% | — |
| FrontierMath Tier 4 | 95% | — |
| ProofBench | 100% | — |
| Omni-MATH | — | 60.2% |
| LMArena Math | — | 1375 |
| MATH Level 5 | — | 84.4% |
| FrontierMath (Feb 2025 set) | — | 4.1% |
| FrontierMath Tier 4 (v1) | — | 0% |

## Knowledge

- Claude Opus 5.5: 66.6 (#9)
- Claude Sonnet 4: 41.6 (#99)

| Benchmark | Claude Opus 5.5 | Claude Sonnet 4 |
|---|---|---|
| GPQA Diamond | 90.6% | 79.2% |
| LMArena Expert | 1564 | 1371 |
| Humanity's Last Exam | — | 7.8% |
| SimpleQA Verified | 72.2% | — |
| MMLU-Pro | — | 84.3% |
| Confabulations | — | 13.2% |
| Vectara Hallucination Rate | — | 10.3% |
| GPQA (HELM) | — | 70.6% |

## Multimodal

- Claude Opus 5.5: 56.5 (#2)
- Claude Sonnet 4: 25.6 (#116)

| Benchmark | Claude Opus 5.5 | Claude Sonnet 4 |
|---|---|---|
| LMArena Vision | — | 1191 |
| GeoBench | — | 37% |
| VPCT | — | 34% |
| Furniture Assembly | 83.3% | — |
| MindCube | — | 44.8% |

## Multilingual

- Claude Opus 5.5: 59.8 (#1)
- Claude Sonnet 4: 46.9 (#151)

| Benchmark | Claude Opus 5.5 | Claude Sonnet 4 |
|---|---|---|
| LMArena Non-English | 1513 | 1333 |
| LMArena Chinese | 1572 | 1351 |
| LMArena Russian | 1532 | 1355 |
| LMArena French | — | 1364 |
| LMArena German | — | 1331 |
| LMArena Japanese | — | 1301 |
| LMArena Korean | — | 1293 |
| LMArena Spanish | — | 1356 |

## Instruction Following

- Claude Opus 5.5: 80.1 (#2)
- Claude Sonnet 4: 71.8 (#141)

| Benchmark | Claude Opus 5.5 | Claude Sonnet 4 |
|---|---|---|
| LMArena Instruction Following | 1535 | 1375 |
| IFEval | — | 84% |

## Long Context

- Claude Opus 5.5: 47.3 (#18)
- Claude Sonnet 4: 33.6 (#254)

| Benchmark | Claude Opus 5.5 | Claude Sonnet 4 |
|---|---|---|
| LMArena Longer Query | 1540 | 1398 |
| Fiction.LiveBench | — | 46.9% |

## Writing & Preference

- Claude Opus 5.5: 78.7 (#3)
- Claude Sonnet 4: 57.3 (#127)

| Benchmark | Claude Opus 5.5 | Claude Sonnet 4 |
|---|---|---|
| LMArena Text | 1518 | 1351 |
| LMArena Creative Writing | 1538 | 1345 |
| EQ-Bench Creative Writing | 2050 | 1483 |
| LMArena Multi-Turn | 1520 | 1376 |
| Short-Story Creative Writing | — | 81.4% |
| WildBench | — | 83.8% |

## FAQ

### Is Claude Opus 5.5 better than Claude Sonnet 4?

Claude Opus 5.5 is the stronger model overall, scoring 68.5 to 40.6 on the Noometry Index.

### Which is cheaper, Claude Opus 5.5 or Claude Sonnet 4?

Claude Sonnet 4 is cheaper. It lists at $3 per million input tokens and $15 per million output tokens; Claude Opus 5.5 lists at $4 and $20.

### Is Claude Opus 5.5 or Claude Sonnet 4 better for coding?

Claude Opus 5.5 scores higher on coding benchmarks: 71.4 versus 44.0 in the Noometry coding category.

### Which has the bigger context window?

Claude Opus 5.5 does, with 1M tokens against 200K.

### How many benchmarks do Claude Opus 5.5 and Claude Sonnet 4 share?

20 benchmarks have published results for both models. Claude Opus 5.5 has 35 scored results on Noometry and Claude Sonnet 4 has 58.