# Claude Sonnet 4.6 vs GPT-5.4 Pro

> GPT-5.4 Pro is the stronger model overall, scoring 58.9 to 50.3 on the Noometry Index. Claude Sonnet 4.6 costs 11× less per token, which makes it the better buy when GPT-5.4 Pro's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/claude-sonnet-4-6-vs-gpt-5-4-pro
- Last updated: 2026-10-12
- Shared benchmarks: 11

## Summary

- They share 11 benchmarks with published results for both. Claude Sonnet 4.6 scores higher in 1 category and GPT-5.4 Pro in 3 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.4 Pro leads 70.7 to 46.1.
- The biggest single-benchmark swing is Chess Puzzles: 13% for Claude Sonnet 4.6 and 58.6% for GPT-5.4 Pro.
- Claude Sonnet 4.6 is cheaper at $3 / $15 per million input/output tokens, against $30 / $180 for GPT-5.4 Pro.
- GPT-5.4 Pro accepts more context: 1.05M tokens versus 1M.

## Snapshot

| | Claude Sonnet 4.6 | GPT-5.4 Pro |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 50.3 | 58.9 |
| Rank | 50 | 18 |
| Context | 1M | 1.05M |
| Input $/M | $3 | $30 |
| Output $/M | $15 | $180 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Sonnet 4.6: 46.3 (#67)
- GPT-5.4 Pro: 43.2 (#90)

| Benchmark | Claude Sonnet 4.6 | GPT-5.4 Pro |
|---|---|---|
| WeirdML | 66.1% | 57.4% |
| SWE-bench Verified | 75.2% | — |
| DeepSWE | 29.9% | — |
| FrontierCode | 24.3% | — |
| LMArena WebDev | 1522 | — |
| SciCode | 46.8% | — |
| LMArena Coding | 1504 | — |
| ALE-Bench | 1,327 | — |

## Agentic & Tool Use

- Claude Sonnet 4.6: 39.1 (#28)
- GPT-5.4 Pro: —

| Benchmark | Claude Sonnet 4.6 | GPT-5.4 Pro |
|---|---|---|
| Terminal-Bench | 53.4% | — |
| APEX-Agents | 43% | — |
| OSWorld 2.0 | 9.3% | — |
| DeepResearch Bench | 54.9% | — |
| OSWorld | 72.1% | — |
| ExploitBench | 23.6% | — |
| GBAEval | 48.8% | — |
| GDP.pdf | 18% | — |
| LMArena Search | 1221 | — |
| Vending-Bench 2 | 7,204 | — |

## Reasoning

- Claude Sonnet 4.6: 46.1 (#45)
- GPT-5.4 Pro: 70.7 (#13)

| Benchmark | Claude Sonnet 4.6 | GPT-5.4 Pro |
|---|---|---|
| ARC-AGI-2 | 60.4% | 83.3% |
| ARC-AGI-1 | 86.5% | 94.5% |
| CritPt | 3.1% | 30% |
| Chess Puzzles | 13% | 58.6% |
| Epoch Capabilities Index | 152.24 | 158.93 |
| SimpleBench | — | 74.1% |
| NYT Connections (extended) | 80.9% | — |
| EnigmaEval | — | 23.8% |
| Thematic Generalization | 76.3% | — |
| LMArena Hard Prompts | 1484 | — |
| Mystery Game Puzzles | 16% | — |
| DTBench | 89.9% | — |
| LMCA | 46.5% | — |
| ForecastBench | 62 | — |

## Math

- Claude Sonnet 4.6: 52.9 (#49)
- GPT-5.4 Pro: 72.4 (#22)

| Benchmark | Claude Sonnet 4.6 | GPT-5.4 Pro |
|---|---|---|
| FrontierMath (Feb 2025 set) | 32.4% | 50% |
| FrontierMath Tier 4 (v1) | 8.3% | 37.5% |
| FrontierMath (Tiers 1-3) | — | 82.5% |
| FrontierMath Tier 4 | — | 58.5% |
| OTIS Mock AIME 2024-2025 | 85.8% | — |
| ProofBench | 45% | — |
| LMArena Math | 1462 | — |

## Knowledge

- Claude Sonnet 4.6: 51.7 (#65)
- GPT-5.4 Pro: 68.3 (#7)

| Benchmark | Claude Sonnet 4.6 | GPT-5.4 Pro |
|---|---|---|
| GPQA Diamond | 87.4% | 94.6% |
| SimpleQA Verified | 35.5% | 46.3% |
| Vectara Hallucination Rate | 10.6% | 8.3% |
| Humanity's Last Exam | — | 44.3% |
| LMArena Expert | 1500 | — |

## Multimodal

- Claude Sonnet 4.6: 38.0 (#68)
- GPT-5.4 Pro: —

| Benchmark | Claude Sonnet 4.6 | GPT-5.4 Pro |
|---|---|---|
| LMArena Vision | 1283 | — |
| Blueprint-Bench 2 | 6.7% | — |
| LMArena Document | 1482 | — |

## Multilingual

- Claude Sonnet 4.6: 54.4 (#41)
- GPT-5.4 Pro: —

| Benchmark | Claude Sonnet 4.6 | GPT-5.4 Pro |
|---|---|---|
| LMArena Non-English | 1440 | — |
| LMArena Chinese | 1491 | — |
| LMArena French | 1465 | — |
| LMArena German | 1428 | — |
| LMArena Japanese | 1420 | — |
| LMArena Korean | 1411 | — |
| LMArena Russian | 1440 | — |
| LMArena Spanish | 1464 | — |

## Instruction Following

- Claude Sonnet 4.6: 77.4 (#25)
- GPT-5.4 Pro: —

| Benchmark | Claude Sonnet 4.6 | GPT-5.4 Pro |
|---|---|---|
| LMArena Instruction Following | 1475 | — |

## Long Context

- Claude Sonnet 4.6: 45.3 (#44)
- GPT-5.4 Pro: —

| Benchmark | Claude Sonnet 4.6 | GPT-5.4 Pro |
|---|---|---|
| LMArena Longer Query | 1479 | — |

## Writing & Preference

- Claude Sonnet 4.6: 70.2 (#22)
- GPT-5.4 Pro: —

| Benchmark | Claude Sonnet 4.6 | GPT-5.4 Pro |
|---|---|---|
| LMArena Text | 1458 | — |
| LMArena Creative Writing | 1435 | — |
| EQ-Bench Creative Writing | 1810 | — |
| EQ-Bench 4 | 1207 | — |
| LMArena Multi-Turn | 1464 | — |

## FAQ

### Is Claude Sonnet 4.6 better than GPT-5.4 Pro?

GPT-5.4 Pro is the stronger model overall, scoring 58.9 to 50.3 on the Noometry Index. Claude Sonnet 4.6 costs 11× less per token, which makes it the better buy when GPT-5.4 Pro's lead doesn't matter for your workload.

### Which is cheaper, Claude Sonnet 4.6 or GPT-5.4 Pro?

Claude Sonnet 4.6 is cheaper. It lists at $3 per million input tokens and $15 per million output tokens; GPT-5.4 Pro lists at $30 and $180.

### Is Claude Sonnet 4.6 or GPT-5.4 Pro better for coding?

Claude Sonnet 4.6 scores higher on coding benchmarks: 46.3 versus 43.2 in the Noometry coding category.

### Which has the bigger context window?

GPT-5.4 Pro does, with 1.05M tokens against 1M.

### How many benchmarks do Claude Sonnet 4.6 and GPT-5.4 Pro share?

11 benchmarks have published results for both models. Claude Sonnet 4.6 has 57 scored results on Noometry and GPT-5.4 Pro has 16.