# Claude 3.5 Sonnet vs Claude Opus 4.5

> Claude Opus 4.5 is the stronger model overall, scoring 50.5 to 34.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-5-sonnet-vs-claude-opus-4-5
- Last updated: 2026-10-10
- Shared benchmarks: 35

## Summary

- They share 35 benchmarks with published results for both. Claude 3.5 Sonnet scores higher in 0 categories and Claude Opus 4.5 in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Claude Opus 4.5 leads 56.5 to 28.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 8.5% for Claude 3.5 Sonnet and 86.1% for Claude Opus 4.5.

## Snapshot

| | Claude 3.5 Sonnet | Claude Opus 4.5 |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Noometry Index | 34.6 | 50.5 |
| Rank | 231 | 47 |
| Context | — | 200K |
| Input $/M | — | $5 |
| Output $/M | — | $25 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude 3.5 Sonnet: 39.0 (#165)
- Claude Opus 4.5: 54.8 (#27)

| Benchmark | Claude 3.5 Sonnet | Claude Opus 4.5 |
|---|---|---|
| GSO | 4.6% | 26.5% |
| WeirdML | 40% | 63.7% |
| LMArena Coding | 1342 | 1504 |
| SWE-bench Verified | — | 76.7% |
| SWE-bench Verified (bash only) | — | 76.8% |
| Aider Polyglot | 51.6% | — |
| LMArena WebDev | — | 1494 |
| SWE-bench Multilingual | — | 70.7% |
| BigCodeBench Instruct | 46.8% | — |
| LiveBench Coding | 67.1% | — |
| BigCodeBench Complete | 58.6% | — |
| CadEval | 48% | — |
| ALE-Bench | — | 1,025 |
| AlgoTune | — | 1.77 |
| HumanEval+ | 81.7% | — |
| MBPP+ | 74.3% | — |

## Agentic & Tool Use

- Claude 3.5 Sonnet: 32.3 (#67)
- Claude Opus 4.5: 47.3 (#12)

| Benchmark | Claude 3.5 Sonnet | Claude Opus 4.5 |
|---|---|---|
| Cybench | 17.5% | 82% |
| BALROG | 32.6% | 43.5% |
| METR Time Horizons | 45.2% | 75% |
| Terminal-Bench | — | 63.1% |
| Berkeley Function Calling Leaderboard | — | 77.5% |
| GDPval | — | 45.5% |
| Remote Labor Index | — | 3.8% |
| TheAgentCompany | 24% | — |
| τ²-bench Airline | — | 84% |
| τ²-bench Banking | — | 24.7% |
| τ²-bench Retail | — | 79.6% |
| τ²-bench Telecom | — | 92.3% |
| DeepResearch Bench | — | 54.8% |
| OSWorld | — | 66.3% |
| LMArena Search | — | 1180 |
| Vending-Bench 2 | — | 4,967 |

## Reasoning

- Claude 3.5 Sonnet: 23.1 (#183)
- Claude Opus 4.5: 42.6 (#51)

| Benchmark | Claude 3.5 Sonnet | Claude Opus 4.5 |
|---|---|---|
| SimpleBench | 41.4% | 62% |
| EnigmaEval | 0.9% | 11.9% |
| LMArena Hard Prompts | 1305 | 1476 |
| DTBench | 67.8% | 89.9% |
| Epoch Capabilities Index | 133.55 | 150.09 |
| ForecastBench | 60.7 | 60.7 |
| ARC-AGI-2 | — | 37.6% |
| Kagi LLM Benchmark | — | 80.2% |
| NYT Connections (extended) | — | 52.5% |
| ARC-AGI-1 | — | 80% |
| Chess Puzzles | — | 12% |
| EBR-Bench | — | 14.3% |
| LiveBench Reasoning | 56.7% | — |
| Mystery Game Puzzles | — | 22% |
| LiveBench Data Analysis | 55% | — |
| LMCA | — | 44.5% |
| LiveBench | 59% | — |

## Math

- Claude 3.5 Sonnet: 19.2 (#288)
- Claude Opus 4.5: 38.6 (#132)

| Benchmark | Claude 3.5 Sonnet | Claude Opus 4.5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | 86.1% |
| LMArena Math | 1307 | 1463 |
| FrontierMath (Feb 2025 set) | 2.1% | 20.7% |
| FrontierMath Tier 4 (v1) | 0% | 4.2% |
| FrontierMath (Tiers 1-3) | — | 34.4% |
| FrontierMath Tier 4 | — | 4.9% |
| ProofBench | — | 36% |
| Omni-MATH | 27.6% | — |
| LiveBench Math | 52.3% | — |
| MATH Level 5 | 56.9% | — |

## Knowledge

- Claude 3.5 Sonnet: 28.6 (#245)
- Claude Opus 4.5: 56.5 (#44)

| Benchmark | Claude 3.5 Sonnet | Claude Opus 4.5 |
|---|---|---|
| GPQA Diamond | 55.3% | 86% |
| Humanity's Last Exam | 4.1% | 25.2% |
| LMArena Expert | 1265 | 1487 |
| SimpleQA Verified | — | 45.7% |
| MMLU-Pro | 77.7% | — |
| Confabulations | 19.9% | — |
| Vectara Hallucination Rate | — | 10.9% |
| GPQA (HELM) | 56.5% | — |
| MMLU | 87.3% | — |

## Multimodal

- Claude 3.5 Sonnet: 26.5 (#120)
- Claude Opus 4.5: 31.4 (#107)

| Benchmark | Claude 3.5 Sonnet | Claude Opus 4.5 |
|---|---|---|
| GeoBench | 62% | 75% |
| VPCT | 33% | 40% |
| LMArena Vision | 1125 | — |
| Video-MME | 60% | — |
| Furniture Assembly | — | 28.3% |
| LMArena Document | — | 1462 |

## Multilingual

- Claude 3.5 Sonnet: 43.2 (#185)
- Claude Opus 4.5: 54.3 (#47)

| Benchmark | Claude 3.5 Sonnet | Claude Opus 4.5 |
|---|---|---|
| LMArena Non-English | 1283 | 1438 |
| LMArena Chinese | 1272 | 1470 |
| LMArena French | 1305 | 1471 |
| LMArena German | 1297 | 1449 |
| LMArena Japanese | 1234 | 1416 |
| LMArena Korean | 1200 | 1424 |
| LMArena Russian | 1306 | 1447 |
| LMArena Spanish | 1290 | 1458 |

## Instruction Following

- Claude 3.5 Sonnet: 68.8 (#182)
- Claude Opus 4.5: 77.5 (#19)

| Benchmark | Claude 3.5 Sonnet | Claude Opus 4.5 |
|---|---|---|
| LMArena Instruction Following | 1297 | 1478 |
| LiveBench Instruction Following | 69.3% | — |
| IFEval | 85.5% | — |

## Long Context

- Claude 3.5 Sonnet: 39.9 (#167)
- Claude Opus 4.5: 46.5 (#22)

| Benchmark | Claude 3.5 Sonnet | Claude Opus 4.5 |
|---|---|---|
| LMArena Longer Query | 1311 | 1480 |
| CL-bench | — | 21.1% |

## Writing & Preference

- Claude 3.5 Sonnet: 52.9 (#164)
- Claude Opus 4.5: 68.1 (#28)

| Benchmark | Claude 3.5 Sonnet | Claude Opus 4.5 |
|---|---|---|
| LMArena Text | 1298 | 1451 |
| LMArena Creative Writing | 1292 | 1445 |
| EQ-Bench Creative Writing | 1451 | 1687 |
| LMArena Multi-Turn | 1326 | 1466 |
| Short-Story Creative Writing | 80.3% | — |
| WildBench | 79.2% | — |
| LiveBench Language | 53.8% | — |

## FAQ

### Is Claude 3.5 Sonnet better than Claude Opus 4.5?

Claude Opus 4.5 is the stronger model overall, scoring 50.5 to 34.6 on the Noometry Index.

### Is Claude 3.5 Sonnet or Claude Opus 4.5 better for coding?

Claude Opus 4.5 scores higher on coding benchmarks: 54.8 versus 39.0 in the Noometry coding category.

### How many benchmarks do Claude 3.5 Sonnet and Claude Opus 4.5 share?

35 benchmarks have published results for both models. Claude 3.5 Sonnet has 60 scored results on Noometry and Claude Opus 4.5 has 69.