# Claude 2 vs GPT-6 Luna

> GPT-6 Luna is the stronger model overall, scoring 45.1 to 24.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-2-vs-gpt-6-luna
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in math, where GPT-6 Luna leads 35.6 to 8.7.

## Snapshot

| | Claude 2 | GPT-6 Luna |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 24.7 | 45.1 |
| Rank | 342 | 65 |
| Context | — | 1.05M |
| Input $/M | — | $0.10 |
| Output $/M | — | $0.50 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude 2: —
- GPT-6 Luna: 54.7 (#24)

| Benchmark | Claude 2 | GPT-6 Luna |
|---|---|---|
| DeepSWE | — | 66.6% |
| FrontierCode | — | 42.4% |
| LMArena WebDev | — | 1583 |
| LMArena Coding | — | 1448 |
| HumanEval+ | 61.6% | — |

## Reasoning

- Claude 2: 20.8 (#213)
- GPT-6 Luna: 31.7 (#68)

| Benchmark | Claude 2 | GPT-6 Luna |
|---|---|---|
| NYT Connections (extended) | — | 68.7% |
| LMArena Hard Prompts | — | 1415 |
| DTBench | 51.9% | — |
| Epoch Capabilities Index | 120.08 | — |

## Math

- Claude 2: 8.7 (#314)
- GPT-6 Luna: 35.6 (#140)

| Benchmark | Claude 2 | GPT-6 Luna |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | — |
| LMArena Math | — | 1396 |
| MATH Level 5 | 11.7% | — |

## Knowledge

- Claude 2: 17.0 (#282)
- GPT-6 Luna: 40.1 (#110)

| Benchmark | Claude 2 | GPT-6 Luna |
|---|---|---|
| GPQA Diamond | 34.7% | — |
| LMArena Expert | — | 1458 |
| MMLU | 78.5% | — |
| TriviaQA | 87.5% | — |

## Multimodal

- Claude 2: —
- GPT-6 Luna: 42.0 (#27)

| Benchmark | Claude 2 | GPT-6 Luna |
|---|---|---|
| Furniture Assembly | — | 44.2% |

## Multilingual

- Claude 2: —
- GPT-6 Luna: 51.0 (#111)

| Benchmark | Claude 2 | GPT-6 Luna |
|---|---|---|
| LMArena Non-English | — | 1390 |
| LMArena Chinese | — | 1425 |
| LMArena Russian | — | 1392 |
| LMArena Spanish | — | 1416 |

## Instruction Following

- Claude 2: —
- GPT-6 Luna: 74.7 (#85)

| Benchmark | Claude 2 | GPT-6 Luna |
|---|---|---|
| LMArena Instruction Following | — | 1414 |

## Long Context

- Claude 2: —
- GPT-6 Luna: 43.3 (#95)

| Benchmark | Claude 2 | GPT-6 Luna |
|---|---|---|
| LMArena Longer Query | — | 1417 |

## Writing & Preference

- Claude 2: —
- GPT-6 Luna: 58.4 (#115)

| Benchmark | Claude 2 | GPT-6 Luna |
|---|---|---|
| LMArena Text | — | 1392 |
| LMArena Creative Writing | — | 1357 |
| LMArena Multi-Turn | — | 1400 |

## FAQ

### Is Claude 2 better than GPT-6 Luna?

GPT-6 Luna is the stronger model overall, scoring 45.1 to 24.7 on the Noometry Index.

### How many benchmarks do Claude 2 and GPT-6 Luna share?

0 benchmarks have published results for both models. Claude 2 has 8 scored results on Noometry and GPT-6 Luna has 18.