# Claude Opus 4.8 vs GPT-5 Pro

> Claude Opus 4.8 is the stronger model overall, scoring 60.7 to 46.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-opus-4-8-vs-gpt-5-pro
- Last updated: 2026-10-10
- Shared benchmarks: 10

## Summary

- They share 10 benchmarks with published results for both. Claude Opus 4.8 scores higher in 4 categories and GPT-5 Pro in 0 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Opus 4.8 leads 78.4 to 48.5.
- The biggest single-benchmark swing is ARC-AGI-2: 72.1% for Claude Opus 4.8 and 18.3% for GPT-5 Pro.
- Claude Opus 4.8 is cheaper at $5 / $25 per million input/output tokens, against $15 / $120 for GPT-5 Pro.
- Claude Opus 4.8 accepts more context: 1M tokens versus 400K.

## Snapshot

| | Claude Opus 4.8 | GPT-5 Pro |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 60.7 | 46.4 |
| Rank | 13 | 64 |
| Context | 1M | 400K |
| Input $/M | $5 | $15 |
| Output $/M | $25 | $120 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Opus 4.8: 59.9 (#12)
- GPT-5 Pro: 44.0 (#80)

| Benchmark | Claude Opus 4.8 | GPT-5 Pro |
|---|---|---|
| WeirdML | 82.9% | 60.4% |
| DeepSWE | 59% | — |
| FrontierCode | 46.5% | — |
| LMArena WebDev | 1556 | — |
| SciCode | 53.5% | — |
| GSO | 47.1% | — |
| LMArena Coding | 1490 | — |
| ALE-Bench | 1,564 | — |
| AlgoTune | — | 1.31 |

## Agentic & Tool Use

- Claude Opus 4.8: 47.6 (#11)
- GPT-5 Pro: —

| Benchmark | Claude Opus 4.8 | GPT-5 Pro |
|---|---|---|
| APEX-Agents | 48.9% | — |
| OSWorld 2.0 | 20.6% | — |
| Remote Labor Index | 8.3% | — |
| τ²-bench Banking | 39.7% | — |
| DeepResearch Bench | 50.2% | — |
| PostTrainBench | 33.8% | — |
| GBAEval | 70.9% | — |
| GDP.pdf | 24% | — |
| LMArena Search | 1204 | — |
| Vending-Bench 2 | 5,787 | — |

## Reasoning

- Claude Opus 4.8: 64.7 (#16)
- GPT-5 Pro: 38.9 (#62)

| Benchmark | Claude Opus 4.8 | GPT-5 Pro |
|---|---|---|
| ARC-AGI-2 | 72.1% | 18.3% |
| SimpleBench | 64.8% | 61.6% |
| Kagi LLM Benchmark | 88.8% | 76.8% |
| ARC-AGI-1 | 92.5% | 70.2% |
| EnigmaEval | 23.5% | 18.8% |
| Epoch Capabilities Index | 158.21 | 150.28 |
| NYT Connections (extended) | 91.1% | — |
| CritPt | 20.9% | — |
| Chess Puzzles | 34% | — |
| EBR-Bench | 28.6% | — |
| LMArena Hard Prompts | 1482 | — |
| Mystery Game Puzzles | 36% | — |
| DTBench | 94.9% | — |
| LMCA | 57.5% | — |
| Surface Evolver Bench | 87.5% | — |
| Bench to the Future 3 | 0.14 | — |
| ForecastBench | 59.9 | — |

## Math

- Claude Opus 4.8: 78.4 (#13)
- GPT-5 Pro: 48.5 (#63)

| Benchmark | Claude Opus 4.8 | GPT-5 Pro |
|---|---|---|
| FrontierMath (Tiers 1-3) | 80% | 55.8% |
| FrontierMath Tier 4 | 56.1% | 19.5% |
| FrontierMath Tier 4 (v1) | 31.3% | 14.6% |
| MathArena Final-Answer Competitions | 91.8% | — |
| OTIS Mock AIME 2024-2025 | 98.3% | — |
| ProofBench | 69% | — |
| LMArena Math | 1487 | — |
| FrontierMath (Feb 2025 set) | 47.2% | — |

## Knowledge

- Claude Opus 4.8: 61.3 (#29)
- GPT-5 Pro: 56.7 (#42)

| Benchmark | Claude Opus 4.8 | GPT-5 Pro |
|---|---|---|
| GPQA Diamond | 91% | — |
| Humanity's Last Exam | — | 31.6% |
| SimpleQA Verified | 53% | — |
| LMArena Expert | 1502 | — |

## Multimodal

- Claude Opus 4.8: 42.9 (#26)
- GPT-5 Pro: —

| Benchmark | Claude Opus 4.8 | GPT-5 Pro |
|---|---|---|
| LMArena Vision | 1294 | — |
| Blueprint-Bench 2 | 14.5% | — |
| Furniture Assembly | 42.5% | — |
| LMArena Document | 1475 | — |

## Multilingual

- Claude Opus 4.8: 55.2 (#33)
- GPT-5 Pro: —

| Benchmark | Claude Opus 4.8 | GPT-5 Pro |
|---|---|---|
| LMArena Non-English | 1450 | — |
| LMArena Chinese | 1507 | — |
| LMArena French | 1481 | — |
| LMArena German | 1472 | — |
| LMArena Japanese | 1440 | — |
| LMArena Korean | 1432 | — |
| LMArena Russian | 1474 | — |
| LMArena Spanish | 1466 | — |

## Instruction Following

- Claude Opus 4.8: 77.4 (#24)
- GPT-5 Pro: —

| Benchmark | Claude Opus 4.8 | GPT-5 Pro |
|---|---|---|
| LMArena Instruction Following | 1476 | — |

## Long Context

- Claude Opus 4.8: 45.4 (#35)
- GPT-5 Pro: —

| Benchmark | Claude Opus 4.8 | GPT-5 Pro |
|---|---|---|
| LMArena Longer Query | 1483 | — |

## Writing & Preference

- Claude Opus 4.8: 72.0 (#16)
- GPT-5 Pro: —

| Benchmark | Claude Opus 4.8 | GPT-5 Pro |
|---|---|---|
| LMArena Text | 1461 | — |
| LMArena Creative Writing | 1454 | — |
| EQ-Bench Creative Writing | 1840 | — |
| EQ-Bench 4 | 1281 | — |
| LMArena Multi-Turn | 1476 | — |

## FAQ

### Is Claude Opus 4.8 better than GPT-5 Pro?

Claude Opus 4.8 is the stronger model overall, scoring 60.7 to 46.4 on the Noometry Index.

### Which is cheaper, Claude Opus 4.8 or GPT-5 Pro?

Claude Opus 4.8 is cheaper. It lists at $5 per million input tokens and $25 per million output tokens; GPT-5 Pro lists at $15 and $120.

### Is Claude Opus 4.8 or GPT-5 Pro better for coding?

Claude Opus 4.8 scores higher on coding benchmarks: 59.9 versus 44.0 in the Noometry coding category.

### Which has the bigger context window?

Claude Opus 4.8 does, with 1M tokens against 400K.

### How many benchmarks do Claude Opus 4.8 and GPT-5 Pro share?

10 benchmarks have published results for both models. Claude Opus 4.8 has 65 scored results on Noometry and GPT-5 Pro has 12.