# Claude Sonnet 5.5 vs GPT-4.5

> Claude Sonnet 5.5 is the stronger model overall, scoring 60.5 to 36.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-sonnet-5-5-vs-gpt-4-5
- Last updated: 2026-10-10
- Shared benchmarks: 2

## Summary

- They share 2 benchmarks with published results for both. Claude Sonnet 5.5 scores higher in 6 categories and GPT-4.5 in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 5.5 leads 88.7 to 31.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 100% for Claude Sonnet 5.5 and 37.8% for GPT-4.5.

## Snapshot

| | Claude Sonnet 5.5 | GPT-4.5 |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 60.5 | 36.9 |
| Rank | 10 | 200 |
| Context | 1M | — |
| Input $/M | $2 | — |
| Output $/M | $10 | — |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Sonnet 5.5: 65.5 (#6)
- GPT-4.5: 41.8 (#102)

| Benchmark | Claude Sonnet 5.5 | GPT-4.5 |
|---|---|---|
| FrontierCode | 52.1% | — |
| Aider Polyglot | — | 44.9% |
| CursorBench | 55.5% | — |
| LMArena WebDev | 1699 | — |
| FrontierSWE | 61.9% | — |
| SciCode | 61% | — |
| WeirdML | — | 39.4% |
| LiveBench Coding | — | 75.2% |
| LMArena Coding | — | 1397 |
| ALE-Bench | 1,819 | — |

## Agentic & Tool Use

- Claude Sonnet 5.5: 44.9 (#14)
- GPT-4.5: 27.6 (#92)

| Benchmark | Claude Sonnet 5.5 | GPT-4.5 |
|---|---|---|
| APEX-Agents | 75.5% | — |
| Cybench | — | 17.5% |

## Reasoning

- Claude Sonnet 5.5: 52.4 (#29)
- GPT-4.5: 14.1 (#320)

| Benchmark | Claude Sonnet 5.5 | GPT-4.5 |
|---|---|---|
| ARC-AGI-2 | — | 0.8% |
| SimpleBench | — | 34.5% |
| ARC-AGI-1 | — | 10.3% |
| CritPt | 31.4% | — |
| EnigmaEval | — | 3.2% |
| LiveBench Reasoning | — | 71.1% |
| LMArena Hard Prompts | — | 1404 |
| Mystery Game Puzzles | 65% | — |
| LiveBench Data Analysis | — | 64.3% |
| Epoch Capabilities Index | — | 136.74 |
| ForecastBench | — | 61.7 |
| LiveBench | — | 69% |

## Math

- Claude Sonnet 5.5: 88.7 (#4)
- GPT-4.5: 31.0 (#200)

| Benchmark | Claude Sonnet 5.5 | GPT-4.5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 100% | 37.8% |
| FrontierMath (Tiers 1-3) | 88.8% | — |
| FrontierMath Tier 4 | 80.5% | — |
| ProofBench | 100% | — |
| LiveBench Math | — | 69.3% |
| LMArena Math | — | 1412 |
| MATH Level 5 | — | 78.6% |

## Knowledge

- Claude Sonnet 5.5: 66.0 (#11)
- GPT-4.5: 32.4 (#205)

| Benchmark | Claude Sonnet 5.5 | GPT-4.5 |
|---|---|---|
| GPQA Diamond | 95.6% | 68.7% |
| Humanity's Last Exam | — | 5.4% |
| SimpleQA Verified | 46.5% | — |
| Confabulations | — | 13.6% |
| LMArena Expert | — | 1394 |

## Multimodal

- Claude Sonnet 5.5: 53.2 (#5)
- GPT-4.5: 37.0 (#68)

| Benchmark | Claude Sonnet 5.5 | GPT-4.5 |
|---|---|---|
| LMArena Vision | — | 1195 |
| VPCT | — | 45% |
| Furniture Assembly | 75% | — |

## Multilingual

- Claude Sonnet 5.5: —
- GPT-4.5: 52.7 (#78)

| Benchmark | Claude Sonnet 5.5 | GPT-4.5 |
|---|---|---|
| LMArena Non-English | — | 1413 |
| LMArena Chinese | — | 1421 |
| LMArena French | — | 1417 |
| LMArena German | — | 1457 |
| LMArena Japanese | — | 1416 |
| LMArena Korean | — | 1392 |
| LMArena Russian | — | 1419 |

## Instruction Following

- Claude Sonnet 5.5: —
- GPT-4.5: 72.8 (#129)

| Benchmark | Claude Sonnet 5.5 | GPT-4.5 |
|---|---|---|
| LiveBench Instruction Following | — | 72.3% |
| LMArena Instruction Following | — | 1404 |

## Long Context

- Claude Sonnet 5.5: —
- GPT-4.5: 40.4 (#150)

| Benchmark | Claude Sonnet 5.5 | GPT-4.5 |
|---|---|---|
| Fiction.LiveBench | — | 63.9% |
| LMArena Longer Query | — | 1406 |

## Writing & Preference

- Claude Sonnet 5.5: —
- GPT-4.5: 57.1 (#129)

| Benchmark | Claude Sonnet 5.5 | GPT-4.5 |
|---|---|---|
| LMArena Text | — | 1417 |
| LMArena Creative Writing | — | 1394 |
| Short-Story Creative Writing | — | 75.6% |
| EQ-Bench Creative Writing | — | 1258 |
| LMArena Multi-Turn | — | 1444 |
| LiveBench Language | — | 61.5% |

## FAQ

### Is Claude Sonnet 5.5 better than GPT-4.5?

Claude Sonnet 5.5 is the stronger model overall, scoring 60.5 to 36.9 on the Noometry Index.

### Is Claude Sonnet 5.5 or GPT-4.5 better for coding?

Claude Sonnet 5.5 scores higher on coding benchmarks: 65.5 versus 41.8 in the Noometry coding category.

### How many benchmarks do Claude Sonnet 5.5 and GPT-4.5 share?

2 benchmarks have published results for both models. Claude Sonnet 5.5 has 16 scored results on Noometry and GPT-4.5 has 42.