# Codellama 34b Instruct vs GPT-4o

> Codellama 34b Instruct is the stronger model overall, scoring 30.2 to 28.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codellama-34b-instruct-vs-gpt-4o
- Last updated: 2026-10-10
- Shared benchmarks: 14

## Summary

- They share 14 benchmarks with published results for both. Codellama 34b Instruct scores higher in 3 categories and GPT-4o in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GPT-4o leads 52.8 to 28.4.
- The biggest single-benchmark swing is BigCodeBench Complete: 37.1% for Codellama 34b Instruct and 61.1% for GPT-4o.
- Codellama 34b Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | Codellama 34b Instruct | GPT-4o |
|---|---|---|
| Provider | Meta | OpenAI |
| Noometry Index | 30.2 | 28.5 |
| Rank | 285 | 316 |
| Context | — | 128K |
| Input $/M | — | $2.50 |
| Output $/M | — | $10 |
| Weights | Open | Proprietary |

## Coding

- Codellama 34b Instruct: 28.0 (#310)
- GPT-4o: 25.1 (#323)

| Benchmark | Codellama 34b Instruct | GPT-4o |
|---|---|---|
| BigCodeBench Instruct | 29% | 51.1% |
| LMArena Coding | 1046 | 1297 |
| BigCodeBench Complete | 37.1% | 61.1% |
| HumanEval+ | 43.9% | 87.2% |
| MBPP+ | 56.3% | 72.2% |
| SWE-bench Verified | — | 31% |
| SWE-bench Verified (bash only) | — | 21.6% |
| Aider Polyglot | — | 45.3% |
| GSO | — | 0% |
| WeirdML | — | 25.1% |
| LiveBench Coding | — | 51.4% |
| CadEval | — | 26% |

## Agentic & Tool Use

- Codellama 34b Instruct: —
- GPT-4o: 20.8 (#133)

| Benchmark | Codellama 34b Instruct | GPT-4o |
|---|---|---|
| GDPval | — | 9.9% |
| TheAgentCompany | — | 8.6% |
| Cybench | — | 12.5% |
| BALROG | — | 32.3% |
| LMArena Search | — | 1006 |
| METR Time Horizons | — | 40.8% |

## Reasoning

- Codellama 34b Instruct: 18.8 (#250)
- GPT-4o: 9.4 (#338)

| Benchmark | Codellama 34b Instruct | GPT-4o |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1281 |
| ARC-AGI-2 | — | 0% |
| SimpleBench | — | 17.8% |
| ARC-AGI-1 | — | 4.5% |
| CritPt | — | 0% |
| Chess Puzzles | — | 13% |
| EnigmaEval | — | 0.8% |
| LiveBench Reasoning | — | 55.8% |
| DTBench | — | 64.5% |
| LiveBench Data Analysis | — | 60.9% |
| LMCA | — | 16.6% |
| Epoch Capabilities Index | — | 128.97 |
| ForecastBench | — | 57.7 |
| LiveBench | — | 55.3% |

## Math

- Codellama 34b Instruct: 28.5 (#227)
- GPT-4o: 10.2 (#303)

| Benchmark | Codellama 34b Instruct | GPT-4o |
|---|---|---|
| LMArena Math | 1056 | 1285 |
| FrontierMath (Tiers 1-3) | — | 0.4% |
| OTIS Mock AIME 2024-2025 | — | 6.4% |
| Omni-MATH | — | 29.3% |
| LiveBench Math | — | 49.5% |
| MATH Level 5 | — | 53.3% |
| FrontierMath (Feb 2025 set) | — | 0.3% |

## Knowledge

- Codellama 34b Instruct: —
- GPT-4o: 28.8 (#235)

| Benchmark | Codellama 34b Instruct | GPT-4o |
|---|---|---|
| GPQA Diamond | — | 49.2% |
| Humanity's Last Exam | — | 2.7% |
| SimpleQA Verified | — | 26% |
| MMLU-Pro | — | 71.3% |
| Confabulations | — | 15.3% |
| Vectara Hallucination Rate | — | 9.6% |
| GPQA (HELM) | — | 52% |
| LMArena Expert | — | 1250 |
| MMLU | — | 88.1% |

## Multimodal

- Codellama 34b Instruct: —
- GPT-4o: 33.9 (#85)

| Benchmark | Codellama 34b Instruct | GPT-4o |
|---|---|---|
| LMArena Vision | — | 1137 |
| Video-MME | — | 71.9% |
| GeoBench | — | 71% |
| VPCT | — | 40% |
| ScienceQA | — | 88.5% |

## Multilingual

- Codellama 34b Instruct: 25.9 (#279)
- GPT-4o: 43.4 (#181)

| Benchmark | Codellama 34b Instruct | GPT-4o |
|---|---|---|
| LMArena Non-English | 1011 | 1283 |
| LMArena Chinese | 976 | 1277 |
| LMArena French | — | 1303 |
| LMArena German | — | 1282 |
| LMArena Japanese | — | 1257 |
| LMArena Korean | — | 1234 |
| LMArena Russian | — | 1286 |
| LMArena Spanish | — | 1292 |

## Instruction Following

- Codellama 34b Instruct: 52.4 (#286)
- GPT-4o: 66.8 (#202)

| Benchmark | Codellama 34b Instruct | GPT-4o |
|---|---|---|
| LMArena Instruction Following | 1028 | 1278 |
| LiveBench Instruction Following | — | 68.6% |
| IFEval | — | 81.7% |

## Long Context

- Codellama 34b Instruct: 30.8 (#279)
- GPT-4o: 39.4 (#174)

| Benchmark | Codellama 34b Instruct | GPT-4o |
|---|---|---|
| LMArena Longer Query | 1014 | 1289 |
| Fiction.LiveBench | — | 66.7% |

## Writing & Preference

- Codellama 34b Instruct: 28.4 (#292)
- GPT-4o: 52.8 (#160)

| Benchmark | Codellama 34b Instruct | GPT-4o |
|---|---|---|
| LMArena Text | 1066 | 1300 |
| LMArena Creative Writing | 1032 | 1291 |
| LMArena Multi-Turn | 1015 | 1302 |
| Short-Story Creative Writing | — | 81.8% |
| WildBench | — | 82.8% |
| LiveBench Language | — | 47.6% |

## FAQ

### Is Codellama 34b Instruct better than GPT-4o?

Codellama 34b Instruct is the stronger model overall, scoring 30.2 to 28.5 on the Noometry Index.

### Is Codellama 34b Instruct or GPT-4o better for coding?

Codellama 34b Instruct scores higher on coding benchmarks: 28.0 versus 25.1 in the Noometry coding category.

### How many benchmarks do Codellama 34b Instruct and GPT-4o share?

14 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and GPT-4o has 72.