# Claude Opus 4.7 vs GPT-5.4

> GPT-5.4 is the stronger model overall, scoring 59.5 to 58.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-opus-4-7-vs-gpt-5-4
- Last updated: 2026-10-10
- Shared benchmarks: 61

## Summary

- They share 61 benchmarks with published results for both. Claude Opus 4.7 scores higher in 5 categories and GPT-5.4 in 5 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.4 leads 61.7 to 53.7.
- The biggest single-benchmark swing is NYT Connections (extended): 39% for Claude Opus 4.7 and 91.3% for GPT-5.4.
- GPT-5.4 is cheaper at $2.50 / $15 per million input/output tokens, against $5 / $25 for Claude Opus 4.7.
- GPT-5.4 accepts more context: 1.05M tokens versus 1M.

## Snapshot

| | Claude Opus 4.7 | GPT-5.4 |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 58.4 | 59.5 |
| Rank | 17 | 14 |
| Context | 1M | 1.05M |
| Input $/M | $5 | $2.50 |
| Output $/M | $25 | $15 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Opus 4.7: 59.9 (#10)
- GPT-5.4: 52.8 (#28)

| Benchmark | Claude Opus 4.7 | GPT-5.4 |
|---|---|---|
| SWE-bench Verified | 83.5% | 76.9% |
| LMArena WebDev | 1557 | 1465 |
| SciCode | 54.5% | 56.6% |
| GSO | 44.1% | 31.4% |
| WeirdML | 76.4% | 77.7% |
| LMArena Coding | 1519 | 1497 |
| MirrorCode | 31.1% | 15.6% |
| ALE-Bench | 1,323 | 1,607 |
| DeepSWE | — | 51.8% |
| FrontierCode | 38.5% | — |
| AlgoTune | — | 1.85 |

## Agentic & Tool Use

- Claude Opus 4.7: 47.9 (#8)
- GPT-5.4: 46.5 (#12)

| Benchmark | Claude Opus 4.7 | GPT-5.4 |
|---|---|---|
| Terminal-Bench | 80.2% | 81.8% |
| APEX-Agents | 49.2% | 52.4% |
| τ²-bench Banking | 40.2% | 39.4% |
| PostTrainBench | 28.6% | 19% |
| GBAEval | 43.8% | 45.1% |
| LMArena Search | 1233 | 1197 |
| Vending-Bench 2 | 10,937 | 6,144 |
| OSWorld 2.0 | 18.2% | — |
| DeepResearch Bench | — | 35.1% |
| ExploitBench | 26.5% | — |
| GDP.pdf | 21% | — |
| METR Time Horizons | — | 74.3% |

## Reasoning

- Claude Opus 4.7: 53.7 (#24)
- GPT-5.4: 61.7 (#17)

| Benchmark | Claude Opus 4.7 | GPT-5.4 |
|---|---|---|
| ARC-AGI-2 | 75.8% | 74% |
| Kagi LLM Benchmark | 80.7% | 63.8% |
| NYT Connections (extended) | 39% | 91.3% |
| ARC-AGI-1 | 93.5% | 93.7% |
| CritPt | 12% | 23.4% |
| Chess Puzzles | 30% | 44% |
| Thematic Generalization | 72.8% | 80% |
| EBR-Bench | 19% | 25.4% |
| LMArena Hard Prompts | 1507 | 1485 |
| Mystery Game Puzzles | 28% | 37% |
| DTBench | 94.7% | 94.4% |
| LMCA | 52.2% | 52% |
| Epoch Capabilities Index | 156.39 | 156.92 |
| ForecastBench | 60.3 | 59.5 |
| SimpleBench | 61.7% | — |
| EnigmaEval | — | 16% |

## Math

- Claude Opus 4.7: 66.5 (#20)
- GPT-5.4: 73.3 (#14)

| Benchmark | Claude Opus 4.7 | GPT-5.4 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 70.2% | 78.6% |
| FrontierMath Tier 4 | 31.7% | 49% |
| MathArena Final-Answer Competitions | 73.6% | 83.1% |
| OTIS Mock AIME 2024-2025 | 97.8% | 97.8% |
| ProofBench | 54% | 56% |
| LMArena Math | 1499 | 1488 |
| FrontierMath (Feb 2025 set) | 43.8% | 47.6% |
| FrontierMath Tier 4 (v1) | 22.9% | 27.1% |

## Knowledge

- Claude Opus 4.7: 62.6 (#20)
- GPT-5.4: 65.3 (#13)

| Benchmark | Claude Opus 4.7 | GPT-5.4 |
|---|---|---|
| GPQA Diamond | 90.2% | 93.3% |
| Humanity's Last Exam | 36.2% | 36.2% |
| SimpleQA Verified | 51.7% | 45.1% |
| Vectara Hallucination Rate | 12% | 7% |
| LMArena Expert | 1521 | 1507 |

## Multimodal

- Claude Opus 4.7: 41.5 (#29)
- GPT-5.4: 43.8 (#19)

| Benchmark | Claude Opus 4.7 | GPT-5.4 |
|---|---|---|
| LMArena Vision | 1317 | 1302 |
| Blueprint-Bench 2 | 24.5% | 27.1% |
| Furniture Assembly | 33.3% | 37.5% |
| LMArena Document | 1495 | 1471 |

## Multilingual

- Claude Opus 4.7: 57.5 (#9)
- GPT-5.4: 56.4 (#22)

| Benchmark | Claude Opus 4.7 | GPT-5.4 |
|---|---|---|
| LMArena Non-English | 1481 | 1465 |
| LMArena Chinese | 1530 | 1520 |
| LMArena French | 1505 | 1493 |
| LMArena German | 1494 | 1472 |
| LMArena Japanese | 1472 | 1484 |
| LMArena Korean | 1466 | 1449 |
| LMArena Russian | 1494 | 1480 |
| LMArena Spanish | 1497 | 1453 |

## Instruction Following

- Claude Opus 4.7: 78.6 (#9)
- GPT-5.4: 77.3 (#25)

| Benchmark | Claude Opus 4.7 | GPT-5.4 |
|---|---|---|
| LMArena Instruction Following | 1498 | 1469 |

## Long Context

- Claude Opus 4.7: 46.1 (#24)
- GPT-5.4: 50.3 (#8)

| Benchmark | Claude Opus 4.7 | GPT-5.4 |
|---|---|---|
| LMArena Longer Query | 1505 | 1474 |
| CL-bench | — | 27.9% |
| CL-bench Life | — | 21.7% |

## Writing & Preference

- Claude Opus 4.7: 75.3 (#8)
- GPT-5.4: 72.1 (#18)

| Benchmark | Claude Opus 4.7 | GPT-5.4 |
|---|---|---|
| LMArena Text | 1491 | 1469 |
| LMArena Creative Writing | 1486 | 1439 |
| EQ-Bench Creative Writing | 1914 | 1840 |
| EQ-Bench 4 | 1311 | 1272 |
| LMArena Multi-Turn | 1506 | 1482 |

## FAQ

### Is Claude Opus 4.7 better than GPT-5.4?

GPT-5.4 is the stronger model overall, scoring 59.5 to 58.4 on the Noometry Index.

### Which is cheaper, Claude Opus 4.7 or GPT-5.4?

GPT-5.4 is cheaper. It lists at $2.50 per million input tokens and $15 per million output tokens; Claude Opus 4.7 lists at $5 and $25.

### Is Claude Opus 4.7 or GPT-5.4 better for coding?

Claude Opus 4.7 scores higher on coding benchmarks: 59.9 versus 52.8 in the Noometry coding category.

### Which has the bigger context window?

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

### How many benchmarks do Claude Opus 4.7 and GPT-5.4 share?

61 benchmarks have published results for both models. Claude Opus 4.7 has 66 scored results on Noometry and GPT-5.4 has 68.