# Claude Opus 4.7 vs GPT-4.5

> Claude Opus 4.7 is the stronger model overall, scoring 58.4 to 36.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-opus-4-7-vs-gpt-4-5
- Last updated: 2026-10-10
- Shared benchmarks: 27

## Summary

- They share 27 benchmarks with published results for both. Claude Opus 4.7 scores higher in 10 categories and GPT-4.5 in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Opus 4.7 leads 53.7 to 14.1.
- The biggest single-benchmark swing is ARC-AGI-1: 93.5% for Claude Opus 4.7 and 10.3% for GPT-4.5.

## Snapshot

| | Claude Opus 4.7 | GPT-4.5 |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 58.4 | 36.9 |
| Rank | 17 | 200 |
| Context | 1M | — |
| Input $/M | $5 | — |
| Output $/M | $25 | — |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Opus 4.7: 59.9 (#10)
- GPT-4.5: 41.8 (#102)

| Benchmark | Claude Opus 4.7 | GPT-4.5 |
|---|---|---|
| WeirdML | 76.4% | 39.4% |
| LMArena Coding | 1519 | 1397 |
| SWE-bench Verified | 83.5% | — |
| FrontierCode | 38.5% | — |
| Aider Polyglot | — | 44.9% |
| LMArena WebDev | 1557 | — |
| SciCode | 54.5% | — |
| GSO | 44.1% | — |
| LiveBench Coding | — | 75.2% |
| MirrorCode | 31.1% | — |
| ALE-Bench | 1,323 | — |

## Agentic & Tool Use

- Claude Opus 4.7: 47.9 (#8)
- GPT-4.5: 27.6 (#92)

| Benchmark | Claude Opus 4.7 | GPT-4.5 |
|---|---|---|
| Terminal-Bench | 80.2% | — |
| APEX-Agents | 49.2% | — |
| OSWorld 2.0 | 18.2% | — |
| τ²-bench Banking | 40.2% | — |
| Cybench | — | 17.5% |
| PostTrainBench | 28.6% | — |
| ExploitBench | 26.5% | — |
| GBAEval | 43.8% | — |
| GDP.pdf | 21% | — |
| LMArena Search | 1233 | — |
| Vending-Bench 2 | 10,937 | — |

## Reasoning

- Claude Opus 4.7: 53.7 (#24)
- GPT-4.5: 14.1 (#320)

| Benchmark | Claude Opus 4.7 | GPT-4.5 |
|---|---|---|
| ARC-AGI-2 | 75.8% | 0.8% |
| SimpleBench | 61.7% | 34.5% |
| ARC-AGI-1 | 93.5% | 10.3% |
| LMArena Hard Prompts | 1507 | 1404 |
| Epoch Capabilities Index | 156.39 | 136.74 |
| ForecastBench | 60.3 | 61.7 |
| Kagi LLM Benchmark | 80.7% | — |
| NYT Connections (extended) | 39% | — |
| CritPt | 12% | — |
| Chess Puzzles | 30% | — |
| EnigmaEval | — | 3.2% |
| Thematic Generalization | 72.8% | — |
| EBR-Bench | 19% | — |
| LiveBench Reasoning | — | 71.1% |
| Mystery Game Puzzles | 28% | — |
| DTBench | 94.7% | — |
| LiveBench Data Analysis | — | 64.3% |
| LMCA | 52.2% | — |
| LiveBench | — | 69% |

## Math

- Claude Opus 4.7: 66.5 (#20)
- GPT-4.5: 31.0 (#200)

| Benchmark | Claude Opus 4.7 | GPT-4.5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 97.8% | 37.8% |
| LMArena Math | 1499 | 1412 |
| FrontierMath (Tiers 1-3) | 70.2% | — |
| FrontierMath Tier 4 | 31.7% | — |
| MathArena Final-Answer Competitions | 73.6% | — |
| ProofBench | 54% | — |
| LiveBench Math | — | 69.3% |
| MATH Level 5 | — | 78.6% |
| FrontierMath (Feb 2025 set) | 43.8% | — |
| FrontierMath Tier 4 (v1) | 22.9% | — |

## Knowledge

- Claude Opus 4.7: 62.6 (#20)
- GPT-4.5: 32.4 (#205)

| Benchmark | Claude Opus 4.7 | GPT-4.5 |
|---|---|---|
| GPQA Diamond | 90.2% | 68.7% |
| Humanity's Last Exam | 36.2% | 5.4% |
| LMArena Expert | 1521 | 1394 |
| SimpleQA Verified | 51.7% | — |
| Confabulations | — | 13.6% |
| Vectara Hallucination Rate | 12% | — |

## Multimodal

- Claude Opus 4.7: 41.5 (#29)
- GPT-4.5: 37.0 (#68)

| Benchmark | Claude Opus 4.7 | GPT-4.5 |
|---|---|---|
| LMArena Vision | 1317 | 1195 |
| VPCT | — | 45% |
| Blueprint-Bench 2 | 24.5% | — |
| Furniture Assembly | 33.3% | — |
| LMArena Document | 1495 | — |

## Multilingual

- Claude Opus 4.7: 57.5 (#9)
- GPT-4.5: 52.7 (#78)

| Benchmark | Claude Opus 4.7 | GPT-4.5 |
|---|---|---|
| LMArena Non-English | 1481 | 1413 |
| LMArena Chinese | 1530 | 1421 |
| LMArena French | 1505 | 1417 |
| LMArena German | 1494 | 1457 |
| LMArena Japanese | 1472 | 1416 |
| LMArena Korean | 1466 | 1392 |
| LMArena Russian | 1494 | 1419 |
| LMArena Spanish | 1497 | — |

## Instruction Following

- Claude Opus 4.7: 78.6 (#9)
- GPT-4.5: 72.8 (#129)

| Benchmark | Claude Opus 4.7 | GPT-4.5 |
|---|---|---|
| LMArena Instruction Following | 1498 | 1404 |
| LiveBench Instruction Following | — | 72.3% |

## Long Context

- Claude Opus 4.7: 46.1 (#24)
- GPT-4.5: 40.4 (#150)

| Benchmark | Claude Opus 4.7 | GPT-4.5 |
|---|---|---|
| LMArena Longer Query | 1505 | 1406 |
| Fiction.LiveBench | — | 63.9% |

## Writing & Preference

- Claude Opus 4.7: 75.3 (#8)
- GPT-4.5: 57.1 (#129)

| Benchmark | Claude Opus 4.7 | GPT-4.5 |
|---|---|---|
| LMArena Text | 1491 | 1417 |
| LMArena Creative Writing | 1486 | 1394 |
| EQ-Bench Creative Writing | 1914 | 1258 |
| LMArena Multi-Turn | 1506 | 1444 |
| Short-Story Creative Writing | — | 75.6% |
| EQ-Bench 4 | 1311 | — |
| LiveBench Language | — | 61.5% |

## FAQ

### Is Claude Opus 4.7 better than GPT-4.5?

Claude Opus 4.7 is the stronger model overall, scoring 58.4 to 36.9 on the Noometry Index.

### Is Claude Opus 4.7 or GPT-4.5 better for coding?

Claude Opus 4.7 scores higher on coding benchmarks: 59.9 versus 41.8 in the Noometry coding category.

### How many benchmarks do Claude Opus 4.7 and GPT-4.5 share?

27 benchmarks have published results for both models. Claude Opus 4.7 has 66 scored results on Noometry and GPT-4.5 has 42.