# Claude 3.7 Sonnet vs GPT-5.4 mini

> GPT-5.4 mini is the stronger model overall, scoring 44.8 to 39.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-7-sonnet-vs-gpt-5-4-mini
- Last updated: 2026-10-10
- Shared benchmarks: 27

## Summary

- They share 27 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 2 categories and GPT-5.4 mini in 8 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5.4 mini leads 51.4 to 39.7.
- The biggest single-benchmark swing is ARC-AGI-1: 28.6% for Claude 3.7 Sonnet and 63.7% for GPT-5.4 mini.

## Snapshot

| | Claude 3.7 Sonnet | GPT-5.4 mini |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 39.4 | 44.8 |
| Rank | 154 | 69 |
| Context | — | 400K |
| Input $/M | — | $0.75 |
| Output $/M | — | $4.50 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude 3.7 Sonnet: 41.1 (#120)
- GPT-5.4 mini: 45.0 (#67)

| Benchmark | Claude 3.7 Sonnet | GPT-5.4 mini |
|---|---|---|
| LMArena Coding | 1361 | 1438 |
| SWE-bench Verified | 61% | — |
| FrontierCode | — | 27% |
| SWE-bench Verified (bash only) | 52.8% | — |
| Aider Polyglot | 64.9% | — |
| LMArena WebDev | — | 1397 |
| SciCode | — | 49.9% |
| GSO | 3.8% | — |
| WeirdML | — | 60.3% |
| LiveBench Coding | 74.5% | — |
| CadEval | 54% | — |
| ALE-Bench | — | 1,189 |

## Agentic & Tool Use

- Claude 3.7 Sonnet: 33.9 (#46)
- GPT-5.4 mini: 29.6 (#74)

| Benchmark | Claude 3.7 Sonnet | GPT-5.4 mini |
|---|---|---|
| DeepResearch Bench | 43.6% | 36.3% |
| TheAgentCompany | 30.9% | — |
| Cybench | 20% | — |
| OSWorld | 35.8% | — |
| METR Time Horizons | 60% | — |

## Reasoning

- Claude 3.7 Sonnet: 18.7 (#252)
- GPT-5.4 mini: 30.3 (#77)

| Benchmark | Claude 3.7 Sonnet | GPT-5.4 mini |
|---|---|---|
| ARC-AGI-2 | 0.9% | 18.9% |
| ARC-AGI-1 | 28.6% | 63.7% |
| LMArena Hard Prompts | 1333 | 1424 |
| Epoch Capabilities Index | 141.16 | 148.83 |
| ForecastBench | 61.8 | 57 |
| SimpleBench | 46.4% | — |
| Kagi LLM Benchmark | — | 37.9% |
| NYT Connections (extended) | — | 61.8% |
| CritPt | — | 10% |
| Chess Puzzles | — | 24% |
| EnigmaEval | 4.2% | — |
| Thematic Generalization | — | 61.7% |
| LiveBench Reasoning | 87.8% | — |
| Mystery Game Puzzles | — | 11% |
| DTBench | — | 80% |
| LiveBench Data Analysis | 74% | — |
| LMCA | — | 40.8% |
| LiveBench | 76.1% | — |

## Math

- Claude 3.7 Sonnet: 35.7 (#137)
- GPT-5.4 mini: 45.4 (#63)

| Benchmark | Claude 3.7 Sonnet | GPT-5.4 mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 88.9% |
| LMArena Math | 1336 | 1418 |
| FrontierMath (Feb 2025 set) | 4.1% | 28.3% |
| FrontierMath (Tiers 1-3) | — | 51.2% |
| FrontierMath Tier 4 | — | 9.8% |
| ProofBench | — | 21% |
| Omni-MATH | 33% | — |
| LiveBench Math | 79% | — |
| MATH Level 5 | 91.2% | — |
| FrontierMath Tier 4 (v1) | — | 2.1% |

## Knowledge

- Claude 3.7 Sonnet: 39.7 (#117)
- GPT-5.4 mini: 51.4 (#62)

| Benchmark | Claude 3.7 Sonnet | GPT-5.4 mini |
|---|---|---|
| GPQA Diamond | 79.7% | 86.9% |
| LMArena Expert | 1321 | 1434 |
| Humanity's Last Exam | 8% | — |
| SimpleQA Verified | — | 29.4% |
| MMLU-Pro | 78.4% | — |
| Confabulations | 14.7% | — |
| Vectara Hallucination Rate | — | 5.5% |
| GPQA (HELM) | 60.8% | — |

## Multimodal

- Claude 3.7 Sonnet: 33.1 (#90)
- GPT-5.4 mini: 39.0 (#51)

| Benchmark | Claude 3.7 Sonnet | GPT-5.4 mini |
|---|---|---|
| LMArena Vision | 1169 | 1245 |
| GeoBench | 68% | — |
| VPCT | 39% | — |
| SpatialViz-Bench | 33.9% | — |

## Multilingual

- Claude 3.7 Sonnet: 44.3 (#174)
- GPT-5.4 mini: 52.1 (#94)

| Benchmark | Claude 3.7 Sonnet | GPT-5.4 mini |
|---|---|---|
| LMArena Non-English | 1296 | 1405 |
| LMArena Chinese | 1299 | 1446 |
| LMArena French | 1302 | 1440 |
| LMArena German | 1301 | 1407 |
| LMArena Japanese | 1268 | 1375 |
| LMArena Korean | 1249 | 1369 |
| LMArena Russian | 1311 | 1417 |
| LMArena Spanish | 1299 | 1403 |

## Instruction Following

- Claude 3.7 Sonnet: 73.1 (#120)
- GPT-5.4 mini: 74.3 (#99)

| Benchmark | Claude 3.7 Sonnet | GPT-5.4 mini |
|---|---|---|
| LMArena Instruction Following | 1352 | 1405 |
| LiveBench Instruction Following | 81.3% | — |
| IFEval | 83.4% | — |

## Long Context

- Claude 3.7 Sonnet: 50.2 (#10)
- GPT-5.4 mini: 42.9 (#107)

| Benchmark | Claude 3.7 Sonnet | GPT-5.4 mini |
|---|---|---|
| LMArena Longer Query | 1373 | 1407 |
| Fiction.LiveBench | 83.3% | — |

## Writing & Preference

- Claude 3.7 Sonnet: 54.6 (#145)
- GPT-5.4 mini: 64.2 (#56)

| Benchmark | Claude 3.7 Sonnet | GPT-5.4 mini |
|---|---|---|
| LMArena Text | 1314 | 1411 |
| LMArena Creative Writing | 1332 | 1370 |
| EQ-Bench Creative Writing | 1412 | 1665 |
| LMArena Multi-Turn | 1339 | 1429 |
| Short-Story Creative Writing | 81.1% | — |
| WildBench | 81.4% | — |
| LiveBench Language | 59.9% | — |

## FAQ

### Is Claude 3.7 Sonnet better than GPT-5.4 mini?

GPT-5.4 mini is the stronger model overall, scoring 44.8 to 39.4 on the Noometry Index.

### Is Claude 3.7 Sonnet or GPT-5.4 mini better for coding?

GPT-5.4 mini scores higher on coding benchmarks: 45.0 versus 41.1 in the Noometry coding category.

### How many benchmarks do Claude 3.7 Sonnet and GPT-5.4 mini share?

27 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and GPT-5.4 mini has 46.