# Codellama 34b Instruct vs GPT-4.5

> GPT-4.5 is the stronger model overall, scoring 36.9 to 30.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codellama-34b-instruct-vs-gpt-4-5
- Last updated: 2026-10-10
- Shared benchmarks: 10

## Summary

- They share 10 benchmarks with published results for both. Codellama 34b Instruct scores higher in 1 category and GPT-4.5 in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GPT-4.5 leads 57.1 to 28.4.
- Codellama 34b Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | Codellama 34b Instruct | GPT-4.5 |
|---|---|---|
| Provider | Meta | OpenAI |
| Noometry Index | 30.2 | 36.9 |
| Rank | 285 | 200 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Proprietary |

## Coding

- Codellama 34b Instruct: 28.0 (#310)
- GPT-4.5: 41.8 (#102)

| Benchmark | Codellama 34b Instruct | GPT-4.5 |
|---|---|---|
| LMArena Coding | 1046 | 1397 |
| Aider Polyglot | — | 44.9% |
| WeirdML | — | 39.4% |
| BigCodeBench Instruct | 29% | — |
| LiveBench Coding | — | 75.2% |
| BigCodeBench Complete | 37.1% | — |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |

## Agentic & Tool Use

- Codellama 34b Instruct: —
- GPT-4.5: 27.6 (#92)

| Benchmark | Codellama 34b Instruct | GPT-4.5 |
|---|---|---|
| Cybench | — | 17.5% |

## Reasoning

- Codellama 34b Instruct: 18.8 (#250)
- GPT-4.5: 14.1 (#320)

| Benchmark | Codellama 34b Instruct | GPT-4.5 |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1404 |
| ARC-AGI-2 | — | 0.8% |
| SimpleBench | — | 34.5% |
| ARC-AGI-1 | — | 10.3% |
| EnigmaEval | — | 3.2% |
| LiveBench Reasoning | — | 71.1% |
| LiveBench Data Analysis | — | 64.3% |
| Epoch Capabilities Index | — | 136.74 |
| ForecastBench | — | 61.7 |
| LiveBench | — | 69% |

## Math

- Codellama 34b Instruct: 28.5 (#227)
- GPT-4.5: 31.0 (#200)

| Benchmark | Codellama 34b Instruct | GPT-4.5 |
|---|---|---|
| LMArena Math | 1056 | 1412 |
| OTIS Mock AIME 2024-2025 | — | 37.8% |
| LiveBench Math | — | 69.3% |
| MATH Level 5 | — | 78.6% |

## Knowledge

- Codellama 34b Instruct: —
- GPT-4.5: 32.4 (#205)

| Benchmark | Codellama 34b Instruct | GPT-4.5 |
|---|---|---|
| GPQA Diamond | — | 68.7% |
| Humanity's Last Exam | — | 5.4% |
| Confabulations | — | 13.6% |
| LMArena Expert | — | 1394 |

## Multimodal

- Codellama 34b Instruct: —
- GPT-4.5: 37.0 (#68)

| Benchmark | Codellama 34b Instruct | GPT-4.5 |
|---|---|---|
| LMArena Vision | — | 1195 |
| VPCT | — | 45% |

## Multilingual

- Codellama 34b Instruct: 25.9 (#279)
- GPT-4.5: 52.7 (#78)

| Benchmark | Codellama 34b Instruct | GPT-4.5 |
|---|---|---|
| LMArena Non-English | 1011 | 1413 |
| LMArena Chinese | 976 | 1421 |
| LMArena French | — | 1417 |
| LMArena German | — | 1457 |
| LMArena Japanese | — | 1416 |
| LMArena Korean | — | 1392 |
| LMArena Russian | — | 1419 |

## Instruction Following

- Codellama 34b Instruct: 52.4 (#286)
- GPT-4.5: 72.8 (#129)

| Benchmark | Codellama 34b Instruct | GPT-4.5 |
|---|---|---|
| LMArena Instruction Following | 1028 | 1404 |
| LiveBench Instruction Following | — | 72.3% |

## Long Context

- Codellama 34b Instruct: 30.8 (#279)
- GPT-4.5: 40.4 (#150)

| Benchmark | Codellama 34b Instruct | GPT-4.5 |
|---|---|---|
| LMArena Longer Query | 1014 | 1406 |
| Fiction.LiveBench | — | 63.9% |

## Writing & Preference

- Codellama 34b Instruct: 28.4 (#292)
- GPT-4.5: 57.1 (#129)

| Benchmark | Codellama 34b Instruct | GPT-4.5 |
|---|---|---|
| LMArena Text | 1066 | 1417 |
| LMArena Creative Writing | 1032 | 1394 |
| LMArena Multi-Turn | 1015 | 1444 |
| Short-Story Creative Writing | — | 75.6% |
| EQ-Bench Creative Writing | — | 1258 |
| LiveBench Language | — | 61.5% |

## FAQ

### Is Codellama 34b Instruct better than GPT-4.5?

GPT-4.5 is the stronger model overall, scoring 36.9 to 30.2 on the Noometry Index.

### Is Codellama 34b Instruct or GPT-4.5 better for coding?

GPT-4.5 scores higher on coding benchmarks: 41.8 versus 28.0 in the Noometry coding category.

### How many benchmarks do Codellama 34b Instruct and GPT-4.5 share?

10 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and GPT-4.5 has 42.