# Claude 3 Sonnet vs Claude Sonnet 5.5

> Claude Sonnet 5.5 is the stronger model overall, scoring 60.5 to 28.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-sonnet-vs-claude-sonnet-5-5
- Last updated: 2026-10-10
- Shared benchmarks: 2

## Summary

- They share 2 benchmarks with published results for both. Claude 3 Sonnet scores higher in 0 categories and Claude Sonnet 5.5 in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 5.5 leads 88.7 to 10.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.5% for Claude 3 Sonnet and 100% for Claude Sonnet 5.5.

## Snapshot

| | Claude 3 Sonnet | Claude Sonnet 5.5 |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Noometry Index | 28.8 | 60.5 |
| Rank | 311 | 10 |
| Context | — | 1M |
| Input $/M | — | $2 |
| Output $/M | — | $10 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude 3 Sonnet: 29.2 (#296)
- Claude Sonnet 5.5: 65.5 (#6)

| Benchmark | Claude 3 Sonnet | Claude Sonnet 5.5 |
|---|---|---|
| FrontierCode | — | 52.1% |
| CursorBench | — | 55.5% |
| LMArena WebDev | — | 1699 |
| FrontierSWE | — | 61.9% |
| SciCode | — | 61% |
| WeirdML | 10.2% | — |
| BigCodeBench Instruct | 42.7% | — |
| LMArena Coding | 1223 | — |
| BigCodeBench Complete | 53.8% | — |
| ALE-Bench | — | 1,819 |
| HumanEval+ | 64% | — |
| MBPP+ | 69.3% | — |

## Agentic & Tool Use

- Claude 3 Sonnet: —
- Claude Sonnet 5.5: 44.9 (#14)

| Benchmark | Claude 3 Sonnet | Claude Sonnet 5.5 |
|---|---|---|
| APEX-Agents | — | 75.5% |

## Reasoning

- Claude 3 Sonnet: 19.7 (#232)
- Claude Sonnet 5.5: 52.4 (#29)

| Benchmark | Claude 3 Sonnet | Claude Sonnet 5.5 |
|---|---|---|
| CritPt | — | 31.4% |
| LMArena Hard Prompts | 1197 | — |
| Mystery Game Puzzles | — | 65% |
| DTBench | 53.6% | — |
| Epoch Capabilities Index | 120.69 | — |
| WinoGrande | 75.1% | — |

## Math

- Claude 3 Sonnet: 10.0 (#305)
- Claude Sonnet 5.5: 88.7 (#4)

| Benchmark | Claude 3 Sonnet | Claude Sonnet 5.5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | 100% |
| FrontierMath (Tiers 1-3) | — | 88.8% |
| FrontierMath Tier 4 | — | 80.5% |
| ProofBench | — | 100% |
| LMArena Math | 1213 | — |
| MATH Level 5 | 18.2% | — |

## Knowledge

- Claude 3 Sonnet: 21.1 (#271)
- Claude Sonnet 5.5: 66.0 (#11)

| Benchmark | Claude 3 Sonnet | Claude Sonnet 5.5 |
|---|---|---|
| GPQA Diamond | 40.6% | 95.6% |
| SimpleQA Verified | — | 46.5% |
| LMArena Expert | 1173 | — |
| MMLU | 75.9% | — |

## Multimodal

- Claude 3 Sonnet: 24.7 (#120)
- Claude Sonnet 5.5: 53.2 (#5)

| Benchmark | Claude 3 Sonnet | Claude Sonnet 5.5 |
|---|---|---|
| LMArena Vision | 984 | — |
| Furniture Assembly | — | 75% |

## Multilingual

- Claude 3 Sonnet: 38.0 (#229)
- Claude Sonnet 5.5: —

| Benchmark | Claude 3 Sonnet | Claude Sonnet 5.5 |
|---|---|---|
| LMArena Non-English | 1205 | — |
| LMArena Chinese | 1188 | — |
| LMArena French | 1228 | — |
| LMArena German | 1204 | — |
| LMArena Japanese | 1131 | — |
| LMArena Korean | 1128 | — |
| LMArena Russian | 1227 | — |
| LMArena Spanish | 1204 | — |

## Instruction Following

- Claude 3 Sonnet: 63.1 (#230)
- Claude Sonnet 5.5: —

| Benchmark | Claude 3 Sonnet | Claude Sonnet 5.5 |
|---|---|---|
| LMArena Instruction Following | 1200 | — |

## Long Context

- Claude 3 Sonnet: 36.7 (#223)
- Claude Sonnet 5.5: —

| Benchmark | Claude 3 Sonnet | Claude Sonnet 5.5 |
|---|---|---|
| LMArena Longer Query | 1211 | — |

## Writing & Preference

- Claude 3 Sonnet: 42.3 (#233)
- Claude Sonnet 5.5: —

| Benchmark | Claude 3 Sonnet | Claude Sonnet 5.5 |
|---|---|---|
| LMArena Text | 1218 | — |
| LMArena Creative Writing | 1186 | — |
| LMArena Multi-Turn | 1227 | — |

## FAQ

### Is Claude 3 Sonnet better than Claude Sonnet 5.5?

Claude Sonnet 5.5 is the stronger model overall, scoring 60.5 to 28.8 on the Noometry Index.

### Is Claude 3 Sonnet or Claude Sonnet 5.5 better for coding?

Claude Sonnet 5.5 scores higher on coding benchmarks: 65.5 versus 29.2 in the Noometry coding category.

### How many benchmarks do Claude 3 Sonnet and Claude Sonnet 5.5 share?

2 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Claude Sonnet 5.5 has 16.