# Codellama 34b Instruct vs GPT-6 Luna

> GPT-6 Luna is the stronger model overall, scoring 53.3 to 30.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codellama-34b-instruct-vs-gpt-6-luna
- Last updated: 2026-10-12
- Shared benchmarks: 10

## Summary

- They share 10 benchmarks with published results for both. Codellama 34b Instruct scores higher in 0 categories and GPT-6 Luna in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6 Luna leads 76.1 to 31.0.
- Codellama 34b Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | Codellama 34b Instruct | GPT-6 Luna |
|---|---|---|
| Provider | Meta | OpenAI |
| Noometry Index | 30.8 | 53.3 |
| Rank | 287 | 36 |
| Context | — | 1.05M |
| Input $/M | — | $0.10 |
| Output $/M | — | $0.50 |
| Weights | Open | Proprietary |

## Coding

- Codellama 34b Instruct: 28.5 (#314)
- GPT-6 Luna: 55.5 (#25)

| Benchmark | Codellama 34b Instruct | GPT-6 Luna |
|---|---|---|
| LMArena Coding | 1046 | 1439 |
| DeepSWE | — | 66.6% |
| FrontierCode | — | 42.4% |
| LMArena WebDev | — | 1581 |
| SciCode | — | 54.6% |
| BigCodeBench Instruct | 29% | — |
| BigCodeBench Complete | 37.1% | — |
| ALE-Bench | — | 1,577 |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |

## Agentic & Tool Use

- Codellama 34b Instruct: —
- GPT-6 Luna: 33.3 (#54)

| Benchmark | Codellama 34b Instruct | GPT-6 Luna |
|---|---|---|
| APEX-Agents | — | 44.3% |
| GDP.pdf | — | 23% |

## Reasoning

- Codellama 34b Instruct: 19.6 (#255)
- GPT-6 Luna: 48.2 (#41)

| Benchmark | Codellama 34b Instruct | GPT-6 Luna |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1411 |
| ARC-AGI-2 | — | 59.3% |
| NYT Connections (extended) | — | 68.7% |
| ARC-AGI-1 | — | 86.7% |
| CritPt | — | 19.4% |
| Chess Puzzles | — | 31% |
| Mystery Game Puzzles | — | 7% |
| DTBench | — | 90.1% |
| LMCA | — | 44.5% |
| Epoch Capabilities Index | — | 156.28 |

## Math

- Codellama 34b Instruct: 31.0 (#230)
- GPT-6 Luna: 76.1 (#15)

| Benchmark | Codellama 34b Instruct | GPT-6 Luna |
|---|---|---|
| LMArena Math | 1056 | 1416 |
| FrontierMath (Tiers 1-3) | — | 78.9% |
| FrontierMath Tier 4 | — | 56.1% |
| OTIS Mock AIME 2024-2025 | — | 98.9% |
| ProofBench | — | 64% |

## Knowledge

- Codellama 34b Instruct: —
- GPT-6 Luna: 57.0 (#41)

| Benchmark | Codellama 34b Instruct | GPT-6 Luna |
|---|---|---|
| GPQA Diamond | — | 90.5% |
| SimpleQA Verified | — | 41.4% |
| LMArena Expert | — | 1444 |

## Multimodal

- Codellama 34b Instruct: —
- GPT-6 Luna: 42.4 (#30)

| Benchmark | Codellama 34b Instruct | GPT-6 Luna |
|---|---|---|
| LMArena Vision | — | 1217 |
| Blueprint-Bench 2 | — | 31.2% |
| Furniture Assembly | — | 44.2% |

## Multilingual

- Codellama 34b Instruct: 25.8 (#284)
- GPT-6 Luna: 50.5 (#117)

| Benchmark | Codellama 34b Instruct | GPT-6 Luna |
|---|---|---|
| LMArena Non-English | 1011 | 1386 |
| LMArena Chinese | 976 | 1433 |
| LMArena French | — | 1420 |
| LMArena German | — | 1369 |
| LMArena Japanese | — | 1369 |
| LMArena Korean | — | 1360 |
| LMArena Russian | — | 1394 |
| LMArena Spanish | — | 1393 |

## Instruction Following

- Codellama 34b Instruct: 52.2 (#291)
- GPT-6 Luna: 74.3 (#99)

| Benchmark | Codellama 34b Instruct | GPT-6 Luna |
|---|---|---|
| LMArena Instruction Following | 1028 | 1409 |

## Long Context

- Codellama 34b Instruct: 30.9 (#284)
- GPT-6 Luna: 43.0 (#111)

| Benchmark | Codellama 34b Instruct | GPT-6 Luna |
|---|---|---|
| LMArena Longer Query | 1013 | 1409 |

## Writing & Preference

- Codellama 34b Instruct: 28.2 (#297)
- GPT-6 Luna: 58.3 (#119)

| Benchmark | Codellama 34b Instruct | GPT-6 Luna |
|---|---|---|
| LMArena Text | 1066 | 1391 |
| LMArena Creative Writing | 1032 | 1363 |
| LMArena Multi-Turn | 1015 | 1396 |

## FAQ

### Is Codellama 34b Instruct better than GPT-6 Luna?

GPT-6 Luna is the stronger model overall, scoring 53.3 to 30.8 on the Noometry Index.

### Is Codellama 34b Instruct or GPT-6 Luna better for coding?

GPT-6 Luna scores higher on coding benchmarks: 55.5 versus 28.5 in the Noometry coding category.

### How many benchmarks do Codellama 34b Instruct and GPT-6 Luna share?

10 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and GPT-6 Luna has 42.