# Claude Opus 4.7 vs GPT-5.2

> Claude Opus 4.7 is the stronger model overall, scoring 58.4 to 54.1 on the Noometry Index. GPT-5.2 costs 2.1× less per token, which makes it the better buy when Claude Opus 4.7's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/claude-opus-4-7-vs-gpt-5-2
- Last updated: 2026-10-10
- Shared benchmarks: 53

## Summary

- They share 53 benchmarks with published results for both. Claude Opus 4.7 scores higher in 9 categories and GPT-5.2 in 1 category; 10 gaps are clear of the uncertainty.
- The widest gap is in multimodal, where GPT-5.2 leads 50.9 to 41.5.
- The biggest single-benchmark swing is NYT Connections (extended): 39% for Claude Opus 4.7 and 83.6% for GPT-5.2.
- GPT-5.2 is cheaper at $1.75 / $14 per million input/output tokens, against $5 / $25 for Claude Opus 4.7.
- Claude Opus 4.7 accepts more context: 1M tokens versus 400K.

## Snapshot

| | Claude Opus 4.7 | GPT-5.2 |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 58.4 | 54.1 |
| Rank | 17 | 31 |
| Context | 1M | 400K |
| Input $/M | $5 | $1.75 |
| Output $/M | $25 | $14 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Opus 4.7: 59.9 (#10)
- GPT-5.2: 52.2 (#32)

| Benchmark | Claude Opus 4.7 | GPT-5.2 |
|---|---|---|
| SWE-bench Verified | 83.5% | 73.8% |
| LMArena WebDev | 1557 | 1415 |
| GSO | 44.1% | 27.4% |
| WeirdML | 76.4% | 72.2% |
| LMArena Coding | 1519 | 1447 |
| ALE-Bench | 1,323 | 1,294 |
| FrontierCode | 38.5% | — |
| SWE-bench Verified (bash only) | — | 72.8% |
| SWE-bench Multilingual | — | 66.7% |
| SciCode | 54.5% | — |
| MirrorCode | 31.1% | — |
| AlgoTune | — | 2.05 |

## Agentic & Tool Use

- Claude Opus 4.7: 47.9 (#8)
- GPT-5.2: 40.0 (#24)

| Benchmark | Claude Opus 4.7 | GPT-5.2 |
|---|---|---|
| Terminal-Bench | 80.2% | 64.9% |
| τ²-bench Banking | 40.2% | 32.2% |
| LMArena Search | 1233 | 1207 |
| Vending-Bench 2 | 10,937 | 3,591 |
| APEX-Agents | 49.2% | — |
| Berkeley Function Calling Leaderboard | — | 55.9% |
| OSWorld 2.0 | 18.2% | — |
| GDPval | — | 49.7% |
| Remote Labor Index | — | 2.5% |
| τ²-bench Airline | — | 83% |
| τ²-bench Retail | — | 81.6% |
| τ²-bench Telecom | — | 89.7% |
| DeepResearch Bench | — | 41.1% |
| PostTrainBench | 28.6% | — |
| ExploitBench | 26.5% | — |
| GBAEval | 43.8% | — |
| GDP.pdf | 21% | — |
| METR Time Horizons | — | 75.3% |

## Reasoning

- Claude Opus 4.7: 53.7 (#24)
- GPT-5.2: 50.1 (#33)

| Benchmark | Claude Opus 4.7 | GPT-5.2 |
|---|---|---|
| ARC-AGI-2 | 75.8% | 52.9% |
| SimpleBench | 61.7% | 45.8% |
| Kagi LLM Benchmark | 80.7% | 73.3% |
| NYT Connections (extended) | 39% | 83.6% |
| ARC-AGI-1 | 93.5% | 86.2% |
| Chess Puzzles | 30% | 49% |
| EBR-Bench | 19% | 23% |
| LMArena Hard Prompts | 1507 | 1445 |
| Mystery Game Puzzles | 28% | 23% |
| DTBench | 94.7% | 90.9% |
| LMCA | 52.2% | 43.9% |
| Epoch Capabilities Index | 156.39 | 153.45 |
| ForecastBench | 60.3 | 60.1 |
| CritPt | 12% | — |
| EnigmaEval | — | 10.4% |
| Thematic Generalization | 72.8% | — |

## Math

- Claude Opus 4.7: 66.5 (#20)
- GPT-5.2: 59.8 (#32)

| Benchmark | Claude Opus 4.7 | GPT-5.2 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 70.2% | 67.4% |
| FrontierMath Tier 4 | 31.7% | 31.7% |
| MathArena Final-Answer Competitions | 73.6% | 72% |
| OTIS Mock AIME 2024-2025 | 97.8% | 96.1% |
| ProofBench | 54% | 15% |
| LMArena Math | 1499 | 1439 |
| FrontierMath (Feb 2025 set) | 43.8% | 40.7% |
| FrontierMath Tier 4 (v1) | 22.9% | 18.8% |

## Knowledge

- Claude Opus 4.7: 62.6 (#20)
- GPT-5.2: 59.2 (#29)

| Benchmark | Claude Opus 4.7 | GPT-5.2 |
|---|---|---|
| GPQA Diamond | 90.2% | 91.4% |
| Humanity's Last Exam | 36.2% | 27.8% |
| SimpleQA Verified | 51.7% | 37.1% |
| Vectara Hallucination Rate | 12% | 8.4% |
| LMArena Expert | 1521 | 1445 |

## Multimodal

- Claude Opus 4.7: 41.5 (#29)
- GPT-5.2: 50.9 (#7)

| Benchmark | Claude Opus 4.7 | GPT-5.2 |
|---|---|---|
| LMArena Vision | 1317 | 1268 |
| Furniture Assembly | 33.3% | 38.3% |
| LMArena Document | 1495 | 1405 |
| VPCT | — | 84% |
| Blueprint-Bench 2 | 24.5% | — |

## Multilingual

- Claude Opus 4.7: 57.5 (#9)
- GPT-5.2: 53.6 (#63)

| Benchmark | Claude Opus 4.7 | GPT-5.2 |
|---|---|---|
| LMArena Non-English | 1481 | 1425 |
| LMArena Chinese | 1530 | 1460 |
| LMArena French | 1505 | 1456 |
| LMArena German | 1494 | 1448 |
| LMArena Japanese | 1472 | 1421 |
| LMArena Korean | 1466 | 1390 |
| LMArena Russian | 1494 | 1440 |
| LMArena Spanish | 1497 | 1433 |

## Instruction Following

- Claude Opus 4.7: 78.6 (#9)
- GPT-5.2: 74.9 (#83)

| Benchmark | Claude Opus 4.7 | GPT-5.2 |
|---|---|---|
| LMArena Instruction Following | 1498 | 1417 |

## Long Context

- Claude Opus 4.7: 46.1 (#24)
- GPT-5.2: 44.0 (#74)

| Benchmark | Claude Opus 4.7 | GPT-5.2 |
|---|---|---|
| LMArena Longer Query | 1505 | 1428 |
| CL-bench | — | 18.2% |

## Writing & Preference

- Claude Opus 4.7: 75.3 (#8)
- GPT-5.2: 67.0 (#30)

| Benchmark | Claude Opus 4.7 | GPT-5.2 |
|---|---|---|
| LMArena Text | 1491 | 1439 |
| LMArena Creative Writing | 1486 | 1402 |
| EQ-Bench Creative Writing | 1914 | 1703 |
| LMArena Multi-Turn | 1506 | 1458 |
| EQ-Bench 4 | 1311 | — |

## FAQ

### Is Claude Opus 4.7 better than GPT-5.2?

Claude Opus 4.7 is the stronger model overall, scoring 58.4 to 54.1 on the Noometry Index. GPT-5.2 costs 2.1× less per token, which makes it the better buy when Claude Opus 4.7's lead doesn't matter for your workload.

### Which is cheaper, Claude Opus 4.7 or GPT-5.2?

GPT-5.2 is cheaper. It lists at $1.75 per million input tokens and $14 per million output tokens; Claude Opus 4.7 lists at $5 and $25.

### Is Claude Opus 4.7 or GPT-5.2 better for coding?

Claude Opus 4.7 scores higher on coding benchmarks: 59.9 versus 52.2 in the Noometry coding category.

### Which has the bigger context window?

Claude Opus 4.7 does, with 1M tokens against 400K.

### How many benchmarks do Claude Opus 4.7 and GPT-5.2 share?

53 benchmarks have published results for both models. Claude Opus 4.7 has 66 scored results on Noometry and GPT-5.2 has 67.