# Claude Opus 5 vs Claude Sonnet 5.5

> Claude Opus 5 is the stronger model overall, scoring 67.8 to 61.9 on the Noometry Index. Claude Sonnet 5.5 costs 2.5× less per token, which makes it the better buy when Claude Opus 5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/claude-opus-5-vs-claude-sonnet-5-5
- Last updated: 2026-10-12
- Shared benchmarks: 31

## Summary

- They share 31 benchmarks with published results for both. Claude Opus 5 scores higher in 8 categories and Claude Sonnet 5.5 in 2 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Opus 5 leads 77.2 to 54.0.
- The biggest single-benchmark swing is Furniture Assembly: 60.8% for Claude Opus 5 and 75% for Claude Sonnet 5.5.
- Claude Sonnet 5.5 is cheaper at $2 / $10 per million input/output tokens, against $5 / $25 for Claude Opus 5.

## Snapshot

| | Claude Opus 5 | Claude Sonnet 5.5 |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Noometry Index | 67.8 | 61.9 |
| Rank | 4 | 10 |
| Context | 1M | 1M |
| Input $/M | $5 | $2 |
| Output $/M | $25 | $10 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Opus 5: 67.5 (#5)
- Claude Sonnet 5.5: 67.3 (#6)

| Benchmark | Claude Opus 5 | Claude Sonnet 5.5 |
|---|---|---|
| FrontierCode | 53.4% | 52.1% |
| CursorBench | 46.6% | 55.5% |
| LMArena WebDev | 1691 | 1774 |
| FrontierSWE | 52% | 61.9% |
| SciCode | 56.4% | 61% |
| LMArena Coding | 1534 | 1513 |
| ALE-Bench | 2,165 | 1,819 |
| DeepSWE | 73.6% | — |
| WeirdML | 91.8% | — |

## Agentic & Tool Use

- Claude Opus 5: 55.6 (#1)
- Claude Sonnet 5.5: 45.0 (#16)

| Benchmark | Claude Opus 5 | Claude Sonnet 5.5 |
|---|---|---|
| APEX-Agents | 65.8% | 75.5% |
| OSWorld 2.0 | 31.4% | — |
| τ²-bench Banking | 48.7% | — |
| PostTrainBench | 35% | — |
| BALROG | 63.4% | — |
| GBAEval | 79.6% | — |
| GDP.pdf | 24% | — |
| Vending-Bench 2 | 11,182 | — |

## Reasoning

- Claude Opus 5: 77.2 (#4)
- Claude Sonnet 5.5: 54.0 (#28)

| Benchmark | Claude Opus 5 | Claude Sonnet 5.5 |
|---|---|---|
| NYT Connections (extended) | 94.3% | 80.5% |
| CritPt | 29.1% | 31.4% |
| LMArena Hard Prompts | 1526 | 1495 |
| Mystery Game Puzzles | 59% | 65% |
| Epoch Capabilities Index | 162.78 | 165.03 |
| ARC-AGI-2 | 90.4% | — |
| SimpleBench | 80.6% | — |
| ARC-AGI-1 | 97.5% | — |
| Chess Puzzles | 42% | — |
| EBR-Bench | 45.7% | — |
| DTBench | 97.9% | — |
| LMCA | 64.5% | — |
| Bench to the Future 3 | 0.12 | — |

## Math

- Claude Opus 5: 86.2 (#8)
- Claude Sonnet 5.5: 87.9 (#6)

| Benchmark | Claude Opus 5 | Claude Sonnet 5.5 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 85.6% | 88.8% |
| FrontierMath Tier 4 | 73.2% | 80.5% |
| OTIS Mock AIME 2024-2025 | 98.9% | 100% |
| ProofBench | 99% | 100% |
| LMArena Math | 1531 | 1510 |
| FrontierMath Erdős | — | 2.9% |

## Knowledge

- Claude Opus 5: 66.8 (#9)
- Claude Sonnet 5.5: 66.0 (#12)

| Benchmark | Claude Opus 5 | Claude Sonnet 5.5 |
|---|---|---|
| GPQA Diamond | 93.9% | 95.6% |
| SimpleQA Verified | 59.9% | 46.5% |
| LMArena Expert | 1557 | 1540 |

## Multimodal

- Claude Opus 5: 50.8 (#8)
- Claude Sonnet 5.5: 51.5 (#6)

| Benchmark | Claude Opus 5 | Claude Sonnet 5.5 |
|---|---|---|
| LMArena Vision | 1319 | 1289 |
| Furniture Assembly | 60.8% | 75% |
| Blueprint-Bench 2 | 30.4% | — |
| LMArena Document | 1516 | — |

## Multilingual

- Claude Opus 5: 58.8 (#4)
- Claude Sonnet 5.5: 55.3 (#30)

| Benchmark | Claude Opus 5 | Claude Sonnet 5.5 |
|---|---|---|
| LMArena Non-English | 1501 | 1452 |
| LMArena Chinese | 1574 | 1522 |
| LMArena Russian | 1507 | 1451 |
| LMArena French | 1519 | — |
| LMArena German | 1524 | — |
| LMArena Japanese | 1516 | — |
| LMArena Korean | 1521 | — |
| LMArena Spanish | 1519 | — |

## Instruction Following

- Claude Opus 5: 79.2 (#7)
- Claude Sonnet 5.5: 78.3 (#11)

| Benchmark | Claude Opus 5 | Claude Sonnet 5.5 |
|---|---|---|
| LMArena Instruction Following | 1517 | 1495 |

## Long Context

- Claude Opus 5: 46.5 (#21)
- Claude Sonnet 5.5: 45.9 (#28)

| Benchmark | Claude Opus 5 | Claude Sonnet 5.5 |
|---|---|---|
| LMArena Longer Query | 1515 | 1498 |

## Writing & Preference

- Claude Opus 5: 79.2 (#1)
- Claude Sonnet 5.5: 66.0 (#40)

| Benchmark | Claude Opus 5 | Claude Sonnet 5.5 |
|---|---|---|
| LMArena Text | 1507 | 1471 |
| LMArena Creative Writing | 1491 | 1465 |
| LMArena Multi-Turn | 1499 | 1474 |
| EQ-Bench Creative Writing | 2133 | — |
| EQ-Bench 4 | 1385 | — |

## FAQ

### Is Claude Opus 5 better than Claude Sonnet 5.5?

Claude Opus 5 is the stronger model overall, scoring 67.8 to 61.9 on the Noometry Index. Claude Sonnet 5.5 costs 2.5× less per token, which makes it the better buy when Claude Opus 5's lead doesn't matter for your workload.

### Which is cheaper, Claude Opus 5 or Claude Sonnet 5.5?

Claude Sonnet 5.5 is cheaper. It lists at $2 per million input tokens and $10 per million output tokens; Claude Opus 5 lists at $5 and $25.

### Is Claude Opus 5 or Claude Sonnet 5.5 better for coding?

They score almost the same on coding (67.5 vs 67.3); test both on your own repository before choosing.

### Which has the bigger context window?

Both accept 1M tokens.

### How many benchmarks do Claude Opus 5 and Claude Sonnet 5.5 share?

31 benchmarks have published results for both models. Claude Opus 5 has 57 scored results on Noometry and Claude Sonnet 5.5 has 32.