# Claude Opus 4.7 vs GPT-5-Codex

> Claude Opus 4.7 is the stronger model overall, scoring 58.3 to 37.9 on the Noometry Index. GPT-5-Codex costs 2.9× 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-codex
- Last updated: 2026-10-10
- Shared benchmarks: 3

## Summary

- They share 3 benchmarks with published results for both. Claude Opus 4.7 scores higher in 3 categories and GPT-5-Codex in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Opus 4.7 leads 53.8 to 30.9.
- The biggest single-benchmark swing is Terminal-Bench: 80.2% for Claude Opus 4.7 and 44.3% for GPT-5-Codex.
- GPT-5-Codex is cheaper at $1.25 / $10 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-Codex |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 58.3 | 37.9 |
| Rank | 19 | 192 |
| Context | 1M | 400K |
| Input $/M | $5 | $1.25 |
| Output $/M | $25 | $10 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Opus 4.7: 59.6 (#13)
- GPT-5-Codex: 42.4 (#103)

| Benchmark | Claude Opus 4.7 | GPT-5-Codex |
|---|---|---|
| WeirdML | 76.4% | 54.5% |
| SWE-bench Verified | 83.5% | — |
| FrontierCode | 38.5% | — |
| LMArena WebDev | 1558 | — |
| SciCode | 54.5% | — |
| GSO | 44.1% | — |
| LMArena Coding | 1518 | — |
| MirrorCode | 31.1% | — |
| ALE-Bench | 1,323 | — |

## Agentic & Tool Use

- Claude Opus 4.7: 47.9 (#10)
- GPT-5-Codex: 31.0 (#72)

| Benchmark | Claude Opus 4.7 | GPT-5-Codex |
|---|---|---|
| Terminal-Bench | 80.2% | 44.3% |
| APEX-Agents | 49.2% | — |
| OSWorld 2.0 | 18.2% | — |
| τ²-bench Banking | 40.2% | — |
| 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: 53.8 (#29)
- GPT-5-Codex: 30.9 (#83)

| Benchmark | Claude Opus 4.7 | GPT-5-Codex |
|---|---|---|
| Kagi LLM Benchmark | 80.7% | 70.3% |
| ARC-AGI-2 | 75.8% | — |
| SimpleBench | 61.7% | — |
| NYT Connections (extended) | 39% | — |
| ARC-AGI-1 | 93.5% | — |
| CritPt | 12% | — |
| Chess Puzzles | 30% | — |
| Thematic Generalization | 72.8% | — |
| EBR-Bench | 19% | — |
| LMArena Hard Prompts | 1506 | — |
| Mystery Game Puzzles | 28% | — |
| DTBench | 94.7% | — |
| LMCA | 52.2% | — |
| Epoch Capabilities Index | 156.25 | — |
| ForecastBench | 60.3 | — |

## Math

- Claude Opus 4.7: 66.7 (#26)
- GPT-5-Codex: —

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

## Knowledge

- Claude Opus 4.7: 62.6 (#23)
- GPT-5-Codex: —

| Benchmark | Claude Opus 4.7 | GPT-5-Codex |
|---|---|---|
| GPQA Diamond | 90.2% | — |
| Humanity's Last Exam | 36.2% | — |
| SimpleQA Verified | 51.7% | — |
| Vectara Hallucination Rate | 12% | — |
| LMArena Expert | 1521 | — |

## Multimodal

- Claude Opus 4.7: 41.2 (#38)
- GPT-5-Codex: —

| Benchmark | Claude Opus 4.7 | GPT-5-Codex |
|---|---|---|
| LMArena Vision | 1316 | — |
| Blueprint-Bench 2 | 24.5% | — |
| Furniture Assembly | 33.3% | — |
| LMArena Document | 1495 | — |

## Multilingual

- Claude Opus 4.7: 57.3 (#10)
- GPT-5-Codex: —

| Benchmark | Claude Opus 4.7 | GPT-5-Codex |
|---|---|---|
| LMArena Non-English | 1480 | — |
| LMArena Chinese | 1531 | — |
| LMArena French | 1503 | — |
| LMArena German | 1495 | — |
| LMArena Japanese | 1472 | — |
| LMArena Korean | 1464 | — |
| LMArena Russian | 1494 | — |
| LMArena Spanish | 1495 | — |

## Instruction Following

- Claude Opus 4.7: 78.4 (#10)
- GPT-5-Codex: —

| Benchmark | Claude Opus 4.7 | GPT-5-Codex |
|---|---|---|
| LMArena Instruction Following | 1498 | — |

## Long Context

- Claude Opus 4.7: 46.2 (#25)
- GPT-5-Codex: —

| Benchmark | Claude Opus 4.7 | GPT-5-Codex |
|---|---|---|
| LMArena Longer Query | 1505 | — |

## Writing & Preference

- Claude Opus 4.7: 75.1 (#8)
- GPT-5-Codex: —

| Benchmark | Claude Opus 4.7 | GPT-5-Codex |
|---|---|---|
| LMArena Text | 1490 | — |
| LMArena Creative Writing | 1486 | — |
| EQ-Bench Creative Writing | 1914 | — |
| EQ-Bench 4 | 1311 | — |
| LMArena Multi-Turn | 1505 | — |

## FAQ

### Is Claude Opus 4.7 better than GPT-5-Codex?

Claude Opus 4.7 is the stronger model overall, scoring 58.3 to 37.9 on the Noometry Index. GPT-5-Codex costs 2.9× 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-Codex?

GPT-5-Codex is cheaper. It lists at $1.25 per million input tokens and $10 per million output tokens; Claude Opus 4.7 lists at $5 and $25.

### Is Claude Opus 4.7 or GPT-5-Codex better for coding?

Claude Opus 4.7 scores higher on coding benchmarks: 59.6 versus 42.4 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-Codex share?

3 benchmarks have published results for both models. Claude Opus 4.7 has 66 scored results on Noometry and GPT-5-Codex has 3.