# Claude 3.7 Sonnet vs GPT-4o

> Claude 3.7 Sonnet is the stronger model overall, scoring 39.4 to 28.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-7-sonnet-vs-gpt-4o
- Last updated: 2026-10-10
- Shared benchmarks: 54

## Summary

- They share 54 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 9 categories and GPT-4o in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude 3.7 Sonnet leads 35.7 to 10.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 57.8% for Claude 3.7 Sonnet and 6.4% for GPT-4o.

## Snapshot

| | Claude 3.7 Sonnet | GPT-4o |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 39.4 | 28.5 |
| Rank | 154 | 316 |
| Context | — | 128K |
| Input $/M | — | $2.50 |
| Output $/M | — | $10 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude 3.7 Sonnet: 41.1 (#120)
- GPT-4o: 25.1 (#323)

| Benchmark | Claude 3.7 Sonnet | GPT-4o |
|---|---|---|
| SWE-bench Verified | 61% | 31% |
| SWE-bench Verified (bash only) | 52.8% | 21.6% |
| Aider Polyglot | 64.9% | 45.3% |
| GSO | 3.8% | 0% |
| LiveBench Coding | 74.5% | 51.4% |
| LMArena Coding | 1361 | 1297 |
| CadEval | 54% | 26% |
| WeirdML | — | 25.1% |
| BigCodeBench Instruct | — | 51.1% |
| BigCodeBench Complete | — | 61.1% |
| HumanEval+ | — | 87.2% |
| MBPP+ | — | 72.2% |

## Agentic & Tool Use

- Claude 3.7 Sonnet: 33.9 (#46)
- GPT-4o: 20.8 (#133)

| Benchmark | Claude 3.7 Sonnet | GPT-4o |
|---|---|---|
| TheAgentCompany | 30.9% | 8.6% |
| Cybench | 20% | 12.5% |
| METR Time Horizons | 60% | 40.8% |
| GDPval | — | 9.9% |
| DeepResearch Bench | 43.6% | — |
| OSWorld | 35.8% | — |
| BALROG | — | 32.3% |
| LMArena Search | — | 1006 |

## Reasoning

- Claude 3.7 Sonnet: 18.7 (#252)
- GPT-4o: 9.4 (#338)

| Benchmark | Claude 3.7 Sonnet | GPT-4o |
|---|---|---|
| ARC-AGI-2 | 0.9% | 0% |
| SimpleBench | 46.4% | 17.8% |
| ARC-AGI-1 | 28.6% | 4.5% |
| EnigmaEval | 4.2% | 0.8% |
| LiveBench Reasoning | 87.8% | 55.8% |
| LMArena Hard Prompts | 1333 | 1281 |
| LiveBench Data Analysis | 74% | 60.9% |
| Epoch Capabilities Index | 141.16 | 128.97 |
| ForecastBench | 61.8 | 57.7 |
| LiveBench | 76.1% | 55.3% |
| CritPt | — | 0% |
| Chess Puzzles | — | 13% |
| DTBench | — | 64.5% |
| LMCA | — | 16.6% |

## Math

- Claude 3.7 Sonnet: 35.7 (#137)
- GPT-4o: 10.2 (#303)

| Benchmark | Claude 3.7 Sonnet | GPT-4o |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 6.4% |
| Omni-MATH | 33% | 29.3% |
| LiveBench Math | 79% | 49.5% |
| LMArena Math | 1336 | 1285 |
| MATH Level 5 | 91.2% | 53.3% |
| FrontierMath (Feb 2025 set) | 4.1% | 0.3% |
| FrontierMath (Tiers 1-3) | — | 0.4% |

## Knowledge

- Claude 3.7 Sonnet: 39.7 (#117)
- GPT-4o: 28.8 (#235)

| Benchmark | Claude 3.7 Sonnet | GPT-4o |
|---|---|---|
| GPQA Diamond | 79.7% | 49.2% |
| Humanity's Last Exam | 8% | 2.7% |
| MMLU-Pro | 78.4% | 71.3% |
| Confabulations | 14.7% | 15.3% |
| GPQA (HELM) | 60.8% | 52% |
| LMArena Expert | 1321 | 1250 |
| SimpleQA Verified | — | 26% |
| Vectara Hallucination Rate | — | 9.6% |
| MMLU | — | 88.1% |

## Multimodal

- Claude 3.7 Sonnet: 33.1 (#90)
- GPT-4o: 33.9 (#85)

| Benchmark | Claude 3.7 Sonnet | GPT-4o |
|---|---|---|
| LMArena Vision | 1169 | 1137 |
| GeoBench | 68% | 71% |
| VPCT | 39% | 40% |
| Video-MME | — | 71.9% |
| ScienceQA | — | 88.5% |
| SpatialViz-Bench | 33.9% | — |

## Multilingual

- Claude 3.7 Sonnet: 44.3 (#174)
- GPT-4o: 43.4 (#181)

| Benchmark | Claude 3.7 Sonnet | GPT-4o |
|---|---|---|
| LMArena Non-English | 1296 | 1283 |
| LMArena Chinese | 1299 | 1277 |
| LMArena French | 1302 | 1303 |
| LMArena German | 1301 | 1282 |
| LMArena Japanese | 1268 | 1257 |
| LMArena Korean | 1249 | 1234 |
| LMArena Russian | 1311 | 1286 |
| LMArena Spanish | 1299 | 1292 |

## Instruction Following

- Claude 3.7 Sonnet: 73.1 (#120)
- GPT-4o: 66.8 (#202)

| Benchmark | Claude 3.7 Sonnet | GPT-4o |
|---|---|---|
| LiveBench Instruction Following | 81.3% | 68.6% |
| IFEval | 83.4% | 81.7% |
| LMArena Instruction Following | 1352 | 1278 |

## Long Context

- Claude 3.7 Sonnet: 50.2 (#10)
- GPT-4o: 39.4 (#174)

| Benchmark | Claude 3.7 Sonnet | GPT-4o |
|---|---|---|
| Fiction.LiveBench | 83.3% | 66.7% |
| LMArena Longer Query | 1373 | 1289 |

## Writing & Preference

- Claude 3.7 Sonnet: 54.6 (#145)
- GPT-4o: 52.8 (#160)

| Benchmark | Claude 3.7 Sonnet | GPT-4o |
|---|---|---|
| LMArena Text | 1314 | 1300 |
| LMArena Creative Writing | 1332 | 1291 |
| Short-Story Creative Writing | 81.1% | 81.8% |
| WildBench | 81.4% | 82.8% |
| LMArena Multi-Turn | 1339 | 1302 |
| LiveBench Language | 59.9% | 47.6% |
| EQ-Bench Creative Writing | 1412 | — |

## FAQ

### Is Claude 3.7 Sonnet better than GPT-4o?

Claude 3.7 Sonnet is the stronger model overall, scoring 39.4 to 28.5 on the Noometry Index.

### Is Claude 3.7 Sonnet or GPT-4o better for coding?

Claude 3.7 Sonnet scores higher on coding benchmarks: 41.1 versus 25.1 in the Noometry coding category.

### How many benchmarks do Claude 3.7 Sonnet and GPT-4o share?

54 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and GPT-4o has 72.