# Claude Sonnet 5 vs GPT-5.1

> Claude Sonnet 5 is the stronger model overall, scoring 54.5 to 48.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-sonnet-5-vs-gpt-5-1
- Last updated: 2026-10-10
- Shared benchmarks: 37

## Summary

- They share 37 benchmarks with published results for both. Claude Sonnet 5 scores higher in 6 categories and GPT-5.1 in 4 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 5 leads 66.1 to 50.3.
- The biggest single-benchmark swing is GSO: 37.3% for Claude Sonnet 5 and 13.7% for GPT-5.1.
- GPT-5.1 is cheaper at $1.25 / $10 per million input/output tokens, against $2 / $10 for Claude Sonnet 5.
- Claude Sonnet 5 accepts more context: 1M tokens versus 400K.

## Snapshot

| | Claude Sonnet 5 | GPT-5.1 |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 54.5 | 48.8 |
| Rank | 26 | 47 |
| Context | 1M | 400K |
| Input $/M | $2 | $1.25 |
| Output $/M | $10 | $10 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Sonnet 5: 55.5 (#20)
- GPT-5.1: 46.9 (#59)

| Benchmark | Claude Sonnet 5 | GPT-5.1 |
|---|---|---|
| LMArena WebDev | 1540 | 1395 |
| SciCode | 53.6% | 43.3% |
| GSO | 37.3% | 13.7% |
| WeirdML | 68.8% | 60.8% |
| LMArena Coding | 1483 | 1454 |
| ALE-Bench | 1,463 | 1,192 |
| SWE-bench Verified | — | 68% |
| DeepSWE | 53.8% | — |
| FrontierCode | 42.7% | — |
| SWE-bench Verified (bash only) | — | 66% |
| CursorBench | 34.1% | — |
| LiveBench Coding | — | 72.5% |

## Agentic & Tool Use

- Claude Sonnet 5: 42.7 (#16)
- GPT-5.1: 32.5 (#55)

| Benchmark | Claude Sonnet 5 | GPT-5.1 |
|---|---|---|
| LMArena Search | 1194 | 1199 |
| Vending-Bench 2 | 6,378 | 1,473 |
| Terminal-Bench | — | 47.6% |
| APEX-Agents | 54.5% | — |
| DeepResearch Bench | — | 42.8% |
| GBAEval | 65.3% | — |

## Reasoning

- Claude Sonnet 5: 48.2 (#37)
- GPT-5.1: 39.9 (#50)

| Benchmark | Claude Sonnet 5 | GPT-5.1 |
|---|---|---|
| SimpleBench | 60.6% | 53.2% |
| CritPt | 16.9% | 4.9% |
| Chess Puzzles | 35% | 32% |
| LMArena Hard Prompts | 1461 | 1457 |
| Mystery Game Puzzles | 35% | 19% |
| DTBench | 92.5% | 90.1% |
| LMCA | 50% | 43.9% |
| Epoch Capabilities Index | 156.34 | 149.66 |
| ForecastBench | 61.1 | 58.1 |
| ARC-AGI-2 | — | 17.6% |
| NYT Connections (extended) | 75.1% | — |
| ARC-AGI-1 | — | 72.8% |
| EnigmaEval | — | 11.2% |
| LiveBench Reasoning | — | 95.8% |
| LiveBench Data Analysis | — | 72.1% |
| Surface Evolver Bench | 60% | — |
| Bench to the Future 3 | 0.14 | — |
| LiveBench | — | 78.8% |

## Math

- Claude Sonnet 5: 66.1 (#21)
- GPT-5.1: 50.3 (#45)

| Benchmark | Claude Sonnet 5 | GPT-5.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 94.7% | 88.6% |
| LMArena Math | 1467 | 1446 |
| FrontierMath (Tiers 1-3) | 65.6% | — |
| FrontierMath Tier 4 | 29.3% | — |
| ProofBench | 77% | — |
| Omni-MATH | — | 46.4% |
| LiveBench Math | — | 94.5% |
| FrontierMath (Feb 2025 set) | — | 31% |
| FrontierMath Tier 4 (v1) | — | 12.5% |

## Knowledge

- Claude Sonnet 5: 55.7 (#42)
- GPT-5.1: 50.5 (#65)

| Benchmark | Claude Sonnet 5 | GPT-5.1 |
|---|---|---|
| GPQA Diamond | 90.5% | 87.6% |
| SimpleQA Verified | 33.7% | 48% |
| LMArena Expert | 1491 | 1470 |
| Humanity's Last Exam | — | 23.7% |
| MMLU-Pro | — | 57.9% |
| Vectara Hallucination Rate | — | 10.9% |
| GPQA (HELM) | — | 44.2% |

## Multimodal

- Claude Sonnet 5: 42.4 (#26)
- GPT-5.1: 44.0 (#17)

| Benchmark | Claude Sonnet 5 | GPT-5.1 |
|---|---|---|
| LMArena Vision | 1275 | 1250 |
| LMArena Document | 1466 | 1403 |
| VPCT | — | 58.7% |
| Blueprint-Bench 2 | 24.9% | — |

## Multilingual

- Claude Sonnet 5: 54.0 (#55)
- GPT-5.1: 54.0 (#51)

| Benchmark | Claude Sonnet 5 | GPT-5.1 |
|---|---|---|
| LMArena Non-English | 1431 | 1431 |
| LMArena Chinese | 1475 | 1495 |
| LMArena French | 1457 | 1451 |
| LMArena German | 1448 | 1439 |
| LMArena Japanese | 1422 | 1453 |
| LMArena Korean | 1411 | 1401 |
| LMArena Russian | 1452 | 1435 |
| LMArena Spanish | 1436 | 1430 |

## Instruction Following

- Claude Sonnet 5: 76.6 (#39)
- GPT-5.1: 84.0 (#1)

| Benchmark | Claude Sonnet 5 | GPT-5.1 |
|---|---|---|
| LMArena Instruction Following | 1453 | 1442 |
| LiveBench Instruction Following | — | 93.3% |
| IFEval | — | 93.5% |

## Long Context

- Claude Sonnet 5: 44.8 (#53)
- GPT-5.1: 47.6 (#14)

| Benchmark | Claude Sonnet 5 | GPT-5.1 |
|---|---|---|
| LMArena Longer Query | 1464 | 1448 |
| CL-bench | — | 23.7% |
| CL-bench Life | — | 17.3% |

## Writing & Preference

- Claude Sonnet 5: 69.4 (#24)
- GPT-5.1: 64.7 (#53)

| Benchmark | Claude Sonnet 5 | GPT-5.1 |
|---|---|---|
| LMArena Text | 1443 | 1443 |
| LMArena Creative Writing | 1416 | 1427 |
| LMArena Multi-Turn | 1454 | 1449 |
| EQ-Bench Creative Writing | 1794 | — |
| WildBench | — | 86.3% |
| EQ-Bench 4 | 1236 | — |
| LiveBench Language | — | 80.2% |

## FAQ

### Is Claude Sonnet 5 better than GPT-5.1?

Claude Sonnet 5 is the stronger model overall, scoring 54.5 to 48.8 on the Noometry Index.

### Which is cheaper, Claude Sonnet 5 or GPT-5.1?

GPT-5.1 is cheaper. It lists at $1.25 per million input tokens and $10 per million output tokens; Claude Sonnet 5 lists at $2 and $10.

### Is Claude Sonnet 5 or GPT-5.1 better for coding?

Claude Sonnet 5 scores higher on coding benchmarks: 55.5 versus 46.9 in the Noometry coding category.

### Which has the bigger context window?

Claude Sonnet 5 does, with 1M tokens against 400K.

### How many benchmarks do Claude Sonnet 5 and GPT-5.1 share?

37 benchmarks have published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and GPT-5.1 has 63.