# Claude Sonnet 5 vs GPT-4

> Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 29.1 on the Noometry Index.

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

## Summary

- They share 27 benchmarks with published results for both. Claude Sonnet 5 scores higher in 8 categories and GPT-4 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 5 leads 66.2 to 10.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 94.7% for Claude Sonnet 5 and 1.1% for GPT-4.
- Claude Sonnet 5 is cheaper at $2 / $10 per million input/output tokens, against $30 / $60 for GPT-4.
- Claude Sonnet 5 accepts more context: 1M tokens versus 8K.

## Snapshot

| | Claude Sonnet 5 | GPT-4 |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 54.6 | 29.1 |
| Rank | 29 | 316 |
| Context | 1M | 8K |
| Input $/M | $2 | $30 |
| Output $/M | $10 | $60 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Sonnet 5: 55.5 (#26)
- GPT-4: 31.6 (#283)

| Benchmark | Claude Sonnet 5 | GPT-4 |
|---|---|---|
| WeirdML | 68.8% | 12.4% |
| LMArena Coding | 1483 | 1254 |
| DeepSWE | 53.8% | — |
| FrontierCode | 42.7% | — |
| CursorBench | 34.1% | — |
| LMArena WebDev | 1541 | — |
| SciCode | 54.3% | — |
| GSO | 37.3% | — |
| BigCodeBench Instruct | — | 46% |
| BigCodeBench Complete | — | 57.2% |
| ALE-Bench | 1,463 | — |
| HumanEval+ | — | 79.3% |

## Agentic & Tool Use

- Claude Sonnet 5: 42.8 (#18)
- GPT-4: —

| Benchmark | Claude Sonnet 5 | GPT-4 |
|---|---|---|
| APEX-Agents | 54.5% | — |
| GBAEval | 65.3% | — |
| LMArena Search | 1194 | — |
| METR Time Horizons | — | 36.1% |
| Vending-Bench 2 | 6,378 | — |

## Reasoning

- Claude Sonnet 5: 49.1 (#39)
- GPT-4: 17.8 (#289)

| Benchmark | Claude Sonnet 5 | GPT-4 |
|---|---|---|
| Chess Puzzles | 35% | 4% |
| LMArena Hard Prompts | 1461 | 1241 |
| Mystery Game Puzzles | 35% | 12% |
| DTBench | 92.5% | 62.7% |
| LMCA | 50% | 17.1% |
| Epoch Capabilities Index | 156.21 | 125.89 |
| ForecastBench | 61.1 | 57.8 |
| SimpleBench | 60.6% | — |
| NYT Connections (extended) | 75.1% | — |
| CritPt | 16.9% | — |
| Surface Evolver Bench | 60% | — |
| Bench to the Future 3 | 0.14 | — |
| BIG-Bench Hard | — | 75.1% |
| HellaSwag | — | 95.3% |
| WinoGrande | — | 87.5% |

## Math

- Claude Sonnet 5: 66.2 (#27)
- GPT-4: 10.8 (#309)

| Benchmark | Claude Sonnet 5 | GPT-4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 94.7% | 1.1% |
| LMArena Math | 1467 | 1269 |
| FrontierMath (Tiers 1-3) | 65.6% | — |
| FrontierMath Tier 4 | 29.3% | — |
| ProofBench | 77% | — |
| MATH Level 5 | — | 23% |
| GSM8K | — | 92% |

## Knowledge

- Claude Sonnet 5: 55.6 (#47)
- GPT-4: 18.4 (#282)

| Benchmark | Claude Sonnet 5 | GPT-4 |
|---|---|---|
| GPQA Diamond | 90.5% | 35.7% |
| LMArena Expert | 1490 | 1211 |
| SimpleQA Verified | 33.7% | — |
| MMLU | — | 86.4% |
| TriviaQA | — | 84.8% |

## Multimodal

- Claude Sonnet 5: 42.4 (#31)
- GPT-4: —

| Benchmark | Claude Sonnet 5 | GPT-4 |
|---|---|---|
| LMArena Vision | 1274 | — |
| Blueprint-Bench 2 | 24.9% | — |
| LMArena Document | 1466 | — |

## Multilingual

- Claude Sonnet 5: 53.8 (#55)
- GPT-4: 40.6 (#215)

| Benchmark | Claude Sonnet 5 | GPT-4 |
|---|---|---|
| LMArena Non-English | 1431 | 1246 |
| LMArena Chinese | 1477 | 1242 |
| LMArena French | 1460 | 1283 |
| LMArena German | 1440 | 1251 |
| LMArena Japanese | 1422 | 1209 |
| LMArena Korean | 1411 | 1184 |
| LMArena Russian | 1451 | 1251 |
| LMArena Spanish | 1437 | 1261 |

## Instruction Following

- Claude Sonnet 5: 76.3 (#41)
- GPT-4: 65.3 (#222)

| Benchmark | Claude Sonnet 5 | GPT-4 |
|---|---|---|
| LMArena Instruction Following | 1452 | 1241 |

## Long Context

- Claude Sonnet 5: 44.8 (#55)
- GPT-4: 37.7 (#212)

| Benchmark | Claude Sonnet 5 | GPT-4 |
|---|---|---|
| LMArena Longer Query | 1463 | 1244 |

## Writing & Preference

- Claude Sonnet 5: 69.2 (#25)
- GPT-4: 34.9 (#268)

| Benchmark | Claude Sonnet 5 | GPT-4 |
|---|---|---|
| LMArena Text | 1442 | 1263 |
| LMArena Creative Writing | 1416 | 1244 |
| EQ-Bench Creative Writing | 1794 | 752 |
| LMArena Multi-Turn | 1454 | 1257 |
| EQ-Bench 4 | 1236 | — |

## FAQ

### Is Claude Sonnet 5 better than GPT-4?

Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 29.1 on the Noometry Index.

### Which is cheaper, Claude Sonnet 5 or GPT-4?

Claude Sonnet 5 is cheaper. It lists at $2 per million input tokens and $10 per million output tokens; GPT-4 lists at $30 and $60.

### Is Claude Sonnet 5 or GPT-4 better for coding?

Claude Sonnet 5 scores higher on coding benchmarks: 55.5 versus 31.6 in the Noometry coding category.

### Which has the bigger context window?

Claude Sonnet 5 does, with 1M tokens against 8K.

### How many benchmarks do Claude Sonnet 5 and GPT-4 share?

27 benchmarks have published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and GPT-4 has 38.