# GPT-5.1-Codex vs GPT-6 Luna

> GPT-6 Luna is the stronger model overall, scoring 45.1 to 38.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-1-codex-vs-gpt-6-luna
- Last updated: 2026-10-10
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. GPT-5.1-Codex scores higher in 0 categories and GPT-6 Luna in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in coding, where GPT-6 Luna leads 54.7 to 41.7.
- GPT-6 Luna is cheaper at $0.10 / $0.50 per million input/output tokens, against $1.25 / $10 for GPT-5.1-Codex.
- GPT-6 Luna accepts more context: 1.05M tokens versus 400K.

## Snapshot

| | GPT-5.1-Codex | GPT-6 Luna |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 38.2 | 45.1 |
| Rank | 178 | 65 |
| Context | 400K | 1.05M |
| Input $/M | $1.25 | $0.10 |
| Output $/M | $10 | $0.50 |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-5.1-Codex: 41.7 (#107)
- GPT-6 Luna: 54.7 (#24)

| Benchmark | GPT-5.1-Codex | GPT-6 Luna |
|---|---|---|
| LMArena WebDev | 1337 | 1583 |
| DeepSWE | — | 66.6% |
| FrontierCode | — | 42.4% |
| SWE-bench Verified (bash only) | 66% | — |
| LMArena Coding | — | 1448 |
| ALE-Bench | 1,245 | — |

## Agentic & Tool Use

- GPT-5.1-Codex: 37.8 (#32)
- GPT-6 Luna: —

| Benchmark | GPT-5.1-Codex | GPT-6 Luna |
|---|---|---|
| Terminal-Bench | 60.4% | — |
| METR Time Horizons | 70.8% | — |

## Reasoning

- GPT-5.1-Codex: —
- GPT-6 Luna: 31.7 (#68)

| Benchmark | GPT-5.1-Codex | GPT-6 Luna |
|---|---|---|
| NYT Connections (extended) | — | 68.7% |
| LMArena Hard Prompts | — | 1415 |

## Math

- GPT-5.1-Codex: 29.3 (#218)
- GPT-6 Luna: 35.6 (#140)

| Benchmark | GPT-5.1-Codex | GPT-6 Luna |
|---|---|---|
| ProofBench | 9% | — |
| LMArena Math | — | 1396 |

## Knowledge

- GPT-5.1-Codex: —
- GPT-6 Luna: 40.1 (#110)

| Benchmark | GPT-5.1-Codex | GPT-6 Luna |
|---|---|---|
| LMArena Expert | — | 1458 |

## Multimodal

- GPT-5.1-Codex: —
- GPT-6 Luna: 42.0 (#27)

| Benchmark | GPT-5.1-Codex | GPT-6 Luna |
|---|---|---|
| Furniture Assembly | — | 44.2% |

## Multilingual

- GPT-5.1-Codex: —
- GPT-6 Luna: 51.0 (#111)

| Benchmark | GPT-5.1-Codex | GPT-6 Luna |
|---|---|---|
| LMArena Non-English | — | 1390 |
| LMArena Chinese | — | 1425 |
| LMArena Russian | — | 1392 |
| LMArena Spanish | — | 1416 |

## Instruction Following

- GPT-5.1-Codex: —
- GPT-6 Luna: 74.7 (#85)

| Benchmark | GPT-5.1-Codex | GPT-6 Luna |
|---|---|---|
| LMArena Instruction Following | — | 1414 |

## Long Context

- GPT-5.1-Codex: —
- GPT-6 Luna: 43.3 (#95)

| Benchmark | GPT-5.1-Codex | GPT-6 Luna |
|---|---|---|
| LMArena Longer Query | — | 1417 |

## Writing & Preference

- GPT-5.1-Codex: —
- GPT-6 Luna: 58.4 (#115)

| Benchmark | GPT-5.1-Codex | GPT-6 Luna |
|---|---|---|
| LMArena Text | — | 1392 |
| LMArena Creative Writing | — | 1357 |
| LMArena Multi-Turn | — | 1400 |

## FAQ

### Is GPT-5.1-Codex better than GPT-6 Luna?

GPT-6 Luna is the stronger model overall, scoring 45.1 to 38.2 on the Noometry Index.

### Which is cheaper, GPT-5.1-Codex or GPT-6 Luna?

GPT-6 Luna is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; GPT-5.1-Codex lists at $1.25 and $10.

### Is GPT-5.1-Codex or GPT-6 Luna better for coding?

GPT-6 Luna scores higher on coding benchmarks: 54.7 versus 41.7 in the Noometry coding category.

### Which has the bigger context window?

GPT-6 Luna does, with 1.05M tokens against 400K.

### How many benchmarks do GPT-5.1-Codex and GPT-6 Luna share?

1 benchmark has published results for both models. GPT-5.1-Codex has 6 scored results on Noometry and GPT-6 Luna has 18.