# Claude Opus 4.5 vs Claude Sonnet 5

> Claude Sonnet 5 is the stronger model overall, scoring 54.5 to 50.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-opus-4-5-vs-claude-sonnet-5
- Last updated: 2026-10-10
- Shared benchmarks: 39

## Summary

- They share 39 benchmarks with published results for both. Claude Opus 4.5 scores higher in 5 categories and Claude Sonnet 5 in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 5 leads 66.1 to 38.5.
- The biggest single-benchmark swing is ProofBench: 36% for Claude Opus 4.5 and 77% for Claude Sonnet 5.
- Claude Sonnet 5 is cheaper at $2 / $10 per million input/output tokens, against $5 / $25 for Claude Opus 4.5.
- Claude Sonnet 5 accepts more context: 1M tokens versus 200K.

## Snapshot

| | Claude Opus 4.5 | Claude Sonnet 5 |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Noometry Index | 50.5 | 54.5 |
| Rank | 39 | 26 |
| Context | 200K | 1M |
| Input $/M | $5 | $2 |
| Output $/M | $25 | $10 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Opus 4.5: 55.4 (#21)
- Claude Sonnet 5: 55.5 (#20)

| Benchmark | Claude Opus 4.5 | Claude Sonnet 5 |
|---|---|---|
| LMArena WebDev | 1493 | 1540 |
| GSO | 26.5% | 37.3% |
| WeirdML | 63.7% | 68.8% |
| LMArena Coding | 1504 | 1483 |
| ALE-Bench | 1,025 | 1,463 |
| SWE-bench Verified | 76.7% | — |
| DeepSWE | — | 53.8% |
| FrontierCode | — | 42.7% |
| SWE-bench Verified (bash only) | 76.8% | — |
| CursorBench | — | 34.1% |
| SWE-bench Multilingual | 70.7% | — |
| SciCode | — | 53.6% |
| AlgoTune | 1.77 | — |

## Agentic & Tool Use

- Claude Opus 4.5: 47.2 (#11)
- Claude Sonnet 5: 42.7 (#16)

| Benchmark | Claude Opus 4.5 | Claude Sonnet 5 |
|---|---|---|
| LMArena Search | 1180 | 1194 |
| Vending-Bench 2 | 4,967 | 6,378 |
| Terminal-Bench | 63.1% | — |
| APEX-Agents | — | 54.5% |
| Berkeley Function Calling Leaderboard | 77.5% | — |
| GDPval | 45.5% | — |
| Remote Labor Index | 3.8% | — |
| τ²-bench Airline | 84% | — |
| τ²-bench Banking | 24.7% | — |
| τ²-bench Retail | 79.6% | — |
| τ²-bench Telecom | 92.3% | — |
| Cybench | 82% | — |
| DeepResearch Bench | 54.8% | — |
| OSWorld | 66.3% | — |
| BALROG | 43.5% | — |
| GBAEval | — | 65.3% |
| METR Time Horizons | 75% | — |

## Reasoning

- Claude Opus 4.5: 42.5 (#43)
- Claude Sonnet 5: 48.2 (#37)

| Benchmark | Claude Opus 4.5 | Claude Sonnet 5 |
|---|---|---|
| SimpleBench | 62% | 60.6% |
| NYT Connections (extended) | 52.5% | 75.1% |
| Chess Puzzles | 12% | 35% |
| LMArena Hard Prompts | 1476 | 1461 |
| Mystery Game Puzzles | 22% | 35% |
| DTBench | 89.9% | 92.5% |
| LMCA | 44.5% | 50% |
| Epoch Capabilities Index | 150.1 | 156.34 |
| ForecastBench | 60.7 | 61.1 |
| ARC-AGI-2 | 37.6% | — |
| Kagi LLM Benchmark | 80.2% | — |
| ARC-AGI-1 | 80% | — |
| CritPt | — | 16.9% |
| EnigmaEval | 11.9% | — |
| EBR-Bench | 14.3% | — |
| Surface Evolver Bench | — | 60% |
| Bench to the Future 3 | — | 0.14 |

## Math

- Claude Opus 4.5: 38.5 (#85)
- Claude Sonnet 5: 66.1 (#21)

| Benchmark | Claude Opus 4.5 | Claude Sonnet 5 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 34.4% | 65.6% |
| FrontierMath Tier 4 | 4.9% | 29.3% |
| OTIS Mock AIME 2024-2025 | 86.1% | 94.7% |
| ProofBench | 36% | 77% |
| LMArena Math | 1463 | 1467 |
| FrontierMath (Feb 2025 set) | 20.7% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |

## Knowledge

- Claude Opus 4.5: 56.4 (#38)
- Claude Sonnet 5: 55.7 (#42)

| Benchmark | Claude Opus 4.5 | Claude Sonnet 5 |
|---|---|---|
| GPQA Diamond | 86% | 90.5% |
| SimpleQA Verified | 45.7% | 33.7% |
| LMArena Expert | 1488 | 1491 |
| Humanity's Last Exam | 25.2% | — |
| Vectara Hallucination Rate | 10.9% | — |

## Multimodal

- Claude Opus 4.5: 31.1 (#99)
- Claude Sonnet 5: 42.4 (#26)

| Benchmark | Claude Opus 4.5 | Claude Sonnet 5 |
|---|---|---|
| LMArena Document | 1462 | 1466 |
| LMArena Vision | — | 1275 |
| GeoBench | 75% | — |
| VPCT | 40% | — |
| Blueprint-Bench 2 | — | 24.9% |
| Furniture Assembly | 28.3% | — |

## Multilingual

- Claude Opus 4.5: 54.5 (#45)
- Claude Sonnet 5: 54.0 (#55)

| Benchmark | Claude Opus 4.5 | Claude Sonnet 5 |
|---|---|---|
| LMArena Non-English | 1438 | 1431 |
| LMArena Chinese | 1470 | 1475 |
| LMArena French | 1471 | 1457 |
| LMArena German | 1449 | 1448 |
| LMArena Japanese | 1415 | 1422 |
| LMArena Korean | 1424 | 1411 |
| LMArena Russian | 1448 | 1452 |
| LMArena Spanish | 1455 | 1436 |

## Instruction Following

- Claude Opus 4.5: 77.7 (#20)
- Claude Sonnet 5: 76.6 (#39)

| Benchmark | Claude Opus 4.5 | Claude Sonnet 5 |
|---|---|---|
| LMArena Instruction Following | 1478 | 1453 |

## Long Context

- Claude Opus 4.5: 46.4 (#21)
- Claude Sonnet 5: 44.8 (#53)

| Benchmark | Claude Opus 4.5 | Claude Sonnet 5 |
|---|---|---|
| LMArena Longer Query | 1480 | 1464 |
| CL-bench | 21.1% | — |

## Writing & Preference

- Claude Opus 4.5: 68.2 (#28)
- Claude Sonnet 5: 69.4 (#24)

| Benchmark | Claude Opus 4.5 | Claude Sonnet 5 |
|---|---|---|
| LMArena Text | 1451 | 1443 |
| LMArena Creative Writing | 1445 | 1416 |
| EQ-Bench Creative Writing | 1687 | 1794 |
| LMArena Multi-Turn | 1466 | 1454 |
| EQ-Bench 4 | — | 1236 |

## FAQ

### Is Claude Opus 4.5 better than Claude Sonnet 5?

Claude Sonnet 5 is the stronger model overall, scoring 54.5 to 50.5 on the Noometry Index.

### Which is cheaper, Claude Opus 4.5 or Claude Sonnet 5?

Claude Sonnet 5 is cheaper. It lists at $2 per million input tokens and $10 per million output tokens; Claude Opus 4.5 lists at $5 and $25.

### Is Claude Opus 4.5 or Claude Sonnet 5 better for coding?

They score almost the same on coding (55.4 vs 55.5); test both on your own repository before choosing.

### Which has the bigger context window?

Claude Sonnet 5 does, with 1M tokens against 200K.

### How many benchmarks do Claude Opus 4.5 and Claude Sonnet 5 share?

39 benchmarks have published results for both models. Claude Opus 4.5 has 69 scored results on Noometry and Claude Sonnet 5 has 51.