# Claude 3 Sonnet vs GPT-5.4 mini

> GPT-5.4 mini is the stronger model overall, scoring 44.8 to 28.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-sonnet-vs-gpt-5-4-mini
- Last updated: 2026-10-10
- Shared benchmarks: 23

## Summary

- They share 23 benchmarks with published results for both. Claude 3 Sonnet scores higher in 0 categories and GPT-5.4 mini in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.4 mini leads 45.4 to 10.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.5% for Claude 3 Sonnet and 88.9% for GPT-5.4 mini.

## Snapshot

| | Claude 3 Sonnet | GPT-5.4 mini |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 28.8 | 44.8 |
| Rank | 311 | 69 |
| Context | — | 400K |
| Input $/M | — | $0.75 |
| Output $/M | — | $4.50 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude 3 Sonnet: 29.2 (#296)
- GPT-5.4 mini: 45.0 (#67)

| Benchmark | Claude 3 Sonnet | GPT-5.4 mini |
|---|---|---|
| WeirdML | 10.2% | 60.3% |
| LMArena Coding | 1223 | 1438 |
| FrontierCode | — | 27% |
| LMArena WebDev | — | 1397 |
| SciCode | — | 49.9% |
| BigCodeBench Instruct | 42.7% | — |
| BigCodeBench Complete | 53.8% | — |
| ALE-Bench | — | 1,189 |
| HumanEval+ | 64% | — |
| MBPP+ | 69.3% | — |

## Agentic & Tool Use

- Claude 3 Sonnet: —
- GPT-5.4 mini: 29.6 (#74)

| Benchmark | Claude 3 Sonnet | GPT-5.4 mini |
|---|---|---|
| DeepResearch Bench | — | 36.3% |

## Reasoning

- Claude 3 Sonnet: 19.7 (#232)
- GPT-5.4 mini: 30.3 (#77)

| Benchmark | Claude 3 Sonnet | GPT-5.4 mini |
|---|---|---|
| LMArena Hard Prompts | 1197 | 1424 |
| DTBench | 53.6% | 80% |
| Epoch Capabilities Index | 120.69 | 148.83 |
| ARC-AGI-2 | — | 18.9% |
| Kagi LLM Benchmark | — | 37.9% |
| NYT Connections (extended) | — | 61.8% |
| ARC-AGI-1 | — | 63.7% |
| CritPt | — | 10% |
| Chess Puzzles | — | 24% |
| Thematic Generalization | — | 61.7% |
| Mystery Game Puzzles | — | 11% |
| LMCA | — | 40.8% |
| ForecastBench | — | 57 |
| WinoGrande | 75.1% | — |

## Math

- Claude 3 Sonnet: 10.0 (#305)
- GPT-5.4 mini: 45.4 (#63)

| Benchmark | Claude 3 Sonnet | GPT-5.4 mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | 88.9% |
| LMArena Math | 1213 | 1418 |
| FrontierMath (Tiers 1-3) | — | 51.2% |
| FrontierMath Tier 4 | — | 9.8% |
| ProofBench | — | 21% |
| MATH Level 5 | 18.2% | — |
| FrontierMath (Feb 2025 set) | — | 28.3% |
| FrontierMath Tier 4 (v1) | — | 2.1% |

## Knowledge

- Claude 3 Sonnet: 21.1 (#271)
- GPT-5.4 mini: 51.4 (#62)

| Benchmark | Claude 3 Sonnet | GPT-5.4 mini |
|---|---|---|
| GPQA Diamond | 40.6% | 86.9% |
| LMArena Expert | 1173 | 1434 |
| SimpleQA Verified | — | 29.4% |
| Vectara Hallucination Rate | — | 5.5% |
| MMLU | 75.9% | — |

## Multimodal

- Claude 3 Sonnet: 24.7 (#120)
- GPT-5.4 mini: 39.0 (#51)

| Benchmark | Claude 3 Sonnet | GPT-5.4 mini |
|---|---|---|
| LMArena Vision | 984 | 1245 |

## Multilingual

- Claude 3 Sonnet: 38.0 (#229)
- GPT-5.4 mini: 52.1 (#94)

| Benchmark | Claude 3 Sonnet | GPT-5.4 mini |
|---|---|---|
| LMArena Non-English | 1205 | 1405 |
| LMArena Chinese | 1188 | 1446 |
| LMArena French | 1228 | 1440 |
| LMArena German | 1204 | 1407 |
| LMArena Japanese | 1131 | 1375 |
| LMArena Korean | 1128 | 1369 |
| LMArena Russian | 1227 | 1417 |
| LMArena Spanish | 1204 | 1403 |

## Instruction Following

- Claude 3 Sonnet: 63.1 (#230)
- GPT-5.4 mini: 74.3 (#99)

| Benchmark | Claude 3 Sonnet | GPT-5.4 mini |
|---|---|---|
| LMArena Instruction Following | 1200 | 1405 |

## Long Context

- Claude 3 Sonnet: 36.7 (#223)
- GPT-5.4 mini: 42.9 (#107)

| Benchmark | Claude 3 Sonnet | GPT-5.4 mini |
|---|---|---|
| LMArena Longer Query | 1211 | 1407 |

## Writing & Preference

- Claude 3 Sonnet: 42.3 (#233)
- GPT-5.4 mini: 64.2 (#56)

| Benchmark | Claude 3 Sonnet | GPT-5.4 mini |
|---|---|---|
| LMArena Text | 1218 | 1411 |
| LMArena Creative Writing | 1186 | 1370 |
| LMArena Multi-Turn | 1227 | 1429 |
| EQ-Bench Creative Writing | — | 1665 |

## FAQ

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

GPT-5.4 mini is the stronger model overall, scoring 44.8 to 28.8 on the Noometry Index.

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

GPT-5.4 mini scores higher on coding benchmarks: 45.0 versus 29.2 in the Noometry coding category.

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

23 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and GPT-5.4 mini has 46.