# Claude 3 Sonnet vs GPT-5.4 Pro

> GPT-5.4 Pro is the stronger model overall, scoring 58.8 to 28.8 on the Noometry Index.

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

## Summary

- They share 3 benchmarks with published results for both. Claude 3 Sonnet scores higher in 0 categories and GPT-5.4 Pro in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.4 Pro leads 72.0 to 10.0.
- The biggest single-benchmark swing is GPQA Diamond: 40.6% for Claude 3 Sonnet and 94.6% for GPT-5.4 Pro.

## Snapshot

| | Claude 3 Sonnet | GPT-5.4 Pro |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 28.8 | 58.8 |
| Rank | 311 | 16 |
| Context | — | 1.05M |
| Input $/M | — | $30 |
| Output $/M | — | $180 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude 3 Sonnet: 29.2 (#296)
- GPT-5.4 Pro: 42.6 (#89)

| Benchmark | Claude 3 Sonnet | GPT-5.4 Pro |
|---|---|---|
| WeirdML | 10.2% | 57.4% |
| BigCodeBench Instruct | 42.7% | — |
| LMArena Coding | 1223 | — |
| BigCodeBench Complete | 53.8% | — |
| HumanEval+ | 64% | — |
| MBPP+ | 69.3% | — |

## Reasoning

- Claude 3 Sonnet: 19.7 (#232)
- GPT-5.4 Pro: 71.0 (#10)

| Benchmark | Claude 3 Sonnet | GPT-5.4 Pro |
|---|---|---|
| Epoch Capabilities Index | 120.69 | 159.12 |
| ARC-AGI-2 | — | 83.3% |
| SimpleBench | — | 74.1% |
| ARC-AGI-1 | — | 94.5% |
| CritPt | — | 30% |
| Chess Puzzles | — | 58.6% |
| EnigmaEval | — | 23.8% |
| LMArena Hard Prompts | 1197 | — |
| DTBench | 53.6% | — |
| WinoGrande | 75.1% | — |

## Math

- Claude 3 Sonnet: 10.0 (#305)
- GPT-5.4 Pro: 72.0 (#17)

| Benchmark | Claude 3 Sonnet | GPT-5.4 Pro |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 82.5% |
| FrontierMath Tier 4 | — | 58.5% |
| OTIS Mock AIME 2024-2025 | 2.5% | — |
| LMArena Math | 1213 | — |
| MATH Level 5 | 18.2% | — |
| FrontierMath (Feb 2025 set) | — | 50% |
| FrontierMath Tier 4 (v1) | — | 37.5% |

## Knowledge

- Claude 3 Sonnet: 21.1 (#271)
- GPT-5.4 Pro: 68.3 (#6)

| Benchmark | Claude 3 Sonnet | GPT-5.4 Pro |
|---|---|---|
| GPQA Diamond | 40.6% | 94.6% |
| Humanity's Last Exam | — | 44.3% |
| SimpleQA Verified | — | 46.3% |
| Vectara Hallucination Rate | — | 8.3% |
| LMArena Expert | 1173 | — |
| MMLU | 75.9% | — |

## Multimodal

- Claude 3 Sonnet: 24.7 (#120)
- GPT-5.4 Pro: —

| Benchmark | Claude 3 Sonnet | GPT-5.4 Pro |
|---|---|---|
| LMArena Vision | 984 | — |

## Multilingual

- Claude 3 Sonnet: 38.0 (#229)
- GPT-5.4 Pro: —

| Benchmark | Claude 3 Sonnet | GPT-5.4 Pro |
|---|---|---|
| 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)
- GPT-5.4 Pro: —

| Benchmark | Claude 3 Sonnet | GPT-5.4 Pro |
|---|---|---|
| LMArena Instruction Following | 1200 | — |

## Long Context

- Claude 3 Sonnet: 36.7 (#223)
- GPT-5.4 Pro: —

| Benchmark | Claude 3 Sonnet | GPT-5.4 Pro |
|---|---|---|
| LMArena Longer Query | 1211 | — |

## Writing & Preference

- Claude 3 Sonnet: 42.3 (#233)
- GPT-5.4 Pro: —

| Benchmark | Claude 3 Sonnet | GPT-5.4 Pro |
|---|---|---|
| LMArena Text | 1218 | — |
| LMArena Creative Writing | 1186 | — |
| LMArena Multi-Turn | 1227 | — |

## FAQ

### Is Claude 3 Sonnet better than GPT-5.4 Pro?

GPT-5.4 Pro is the stronger model overall, scoring 58.8 to 28.8 on the Noometry Index.

### Is Claude 3 Sonnet or GPT-5.4 Pro better for coding?

GPT-5.4 Pro scores higher on coding benchmarks: 42.6 versus 29.2 in the Noometry coding category.

### How many benchmarks do Claude 3 Sonnet and GPT-5.4 Pro share?

3 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and GPT-5.4 Pro has 16.