# Codellama 70b Instruct vs GPT-6 Luna

> GPT-6 Luna is the stronger model overall, scoring 45.1 to 33.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codellama-70b-instruct-vs-gpt-6-luna
- Last updated: 2026-10-10
- Shared benchmarks: 4

## Summary

- They share 4 benchmarks with published results for both. Codellama 70b Instruct scores higher in 0 categories and GPT-6 Luna in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where GPT-6 Luna leads 51.0 to 24.9.
- Codellama 70b Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | Codellama 70b Instruct | GPT-6 Luna |
|---|---|---|
| Provider | Meta | OpenAI |
| Noometry Index | 33.3 | 45.1 |
| Rank | 236 | 65 |
| Context | — | 1.05M |
| Input $/M | — | $0.10 |
| Output $/M | — | $0.50 |
| Weights | Open | Proprietary |

## Coding

- Codellama 70b Instruct: 37.0 (#189)
- GPT-6 Luna: 54.7 (#24)

| Benchmark | Codellama 70b Instruct | GPT-6 Luna |
|---|---|---|
| DeepSWE | — | 66.6% |
| FrontierCode | — | 42.4% |
| LMArena WebDev | — | 1583 |
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1448 |
| BigCodeBench Complete | 49.6% | — |
| HumanEval+ | 65.9% | — |

## Reasoning

- Codellama 70b Instruct: 19.2 (#241)
- GPT-6 Luna: 31.7 (#68)

| Benchmark | Codellama 70b Instruct | GPT-6 Luna |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1415 |
| NYT Connections (extended) | — | 68.7% |

## Math

- Codellama 70b Instruct: —
- GPT-6 Luna: 35.6 (#140)

| Benchmark | Codellama 70b Instruct | GPT-6 Luna |
|---|---|---|
| LMArena Math | — | 1396 |

## Knowledge

- Codellama 70b Instruct: —
- GPT-6 Luna: 40.1 (#110)

| Benchmark | Codellama 70b Instruct | GPT-6 Luna |
|---|---|---|
| LMArena Expert | — | 1458 |

## Multimodal

- Codellama 70b Instruct: —
- GPT-6 Luna: 42.0 (#27)

| Benchmark | Codellama 70b Instruct | GPT-6 Luna |
|---|---|---|
| Furniture Assembly | — | 44.2% |

## Multilingual

- Codellama 70b Instruct: 24.9 (#283)
- GPT-6 Luna: 51.0 (#111)

| Benchmark | Codellama 70b Instruct | GPT-6 Luna |
|---|---|---|
| LMArena Non-English | 992 | 1390 |
| LMArena Chinese | — | 1425 |
| LMArena Russian | — | 1392 |
| LMArena Spanish | — | 1416 |

## Instruction Following

- Codellama 70b Instruct: 52.1 (#288)
- GPT-6 Luna: 74.7 (#85)

| Benchmark | Codellama 70b Instruct | GPT-6 Luna |
|---|---|---|
| LMArena Instruction Following | 1024 | 1414 |

## Long Context

- Codellama 70b Instruct: —
- GPT-6 Luna: 43.3 (#95)

| Benchmark | Codellama 70b Instruct | GPT-6 Luna |
|---|---|---|
| LMArena Longer Query | — | 1417 |

## Writing & Preference

- Codellama 70b Instruct: 33.6 (#272)
- GPT-6 Luna: 58.4 (#115)

| Benchmark | Codellama 70b Instruct | GPT-6 Luna |
|---|---|---|
| LMArena Text | 1057 | 1392 |
| LMArena Creative Writing | — | 1357 |
| LMArena Multi-Turn | — | 1400 |

## FAQ

### Is Codellama 70b Instruct better than GPT-6 Luna?

GPT-6 Luna is the stronger model overall, scoring 45.1 to 33.3 on the Noometry Index.

### Is Codellama 70b Instruct or GPT-6 Luna better for coding?

GPT-6 Luna scores higher on coding benchmarks: 54.7 versus 37.0 in the Noometry coding category.

### How many benchmarks do Codellama 70b Instruct and GPT-6 Luna share?

4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and GPT-6 Luna has 18.