# Codellama 70b Instruct vs GPT-4.5

> GPT-4.5 is the stronger model overall, scoring 37.2 to 33.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codellama-70b-instruct-vs-gpt-4-5
- Last updated: 2026-10-10
- Shared benchmarks: 4

## Summary

- They share 4 benchmarks with published results for both. Codellama 70b Instruct scores higher in 1 category and GPT-4.5 in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where GPT-4.5 leads 52.5 to 24.8.
- Codellama 70b Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | Codellama 70b Instruct | GPT-4.5 |
|---|---|---|
| Provider | Meta | OpenAI |
| Noometry Index | 33.7 | 37.2 |
| Rank | 237 | 208 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Proprietary |

## Coding

- Codellama 70b Instruct: 37.6 (#193)
- GPT-4.5: 42.2 (#109)

| Benchmark | Codellama 70b Instruct | GPT-4.5 |
|---|---|---|
| Aider Polyglot | — | 44.9% |
| WeirdML | — | 39.4% |
| BigCodeBench Instruct | 40.7% | — |
| LiveBench Coding | — | 75.2% |
| LMArena Coding | — | 1396 |
| BigCodeBench Complete | 49.6% | — |
| HumanEval+ | 65.9% | — |

## Agentic & Tool Use

- Codellama 70b Instruct: —
- GPT-4.5: 27.9 (#97)

| Benchmark | Codellama 70b Instruct | GPT-4.5 |
|---|---|---|
| Cybench | — | 17.5% |

## Reasoning

- Codellama 70b Instruct: 20.1 (#242)
- GPT-4.5: 13.9 (#330)

| Benchmark | Codellama 70b Instruct | GPT-4.5 |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1403 |
| 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 70b Instruct: —
- GPT-4.5: 32.6 (#211)

| Benchmark | Codellama 70b Instruct | GPT-4.5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 37.8% |
| LiveBench Math | — | 69.3% |
| LMArena Math | — | 1412 |
| MATH Level 5 | — | 78.6% |

## Knowledge

- Codellama 70b Instruct: —
- GPT-4.5: 32.5 (#211)

| Benchmark | Codellama 70b Instruct | GPT-4.5 |
|---|---|---|
| GPQA Diamond | — | 68.7% |
| Humanity's Last Exam | — | 5.4% |
| Confabulations | — | 13.6% |
| LMArena Expert | — | 1394 |

## Multimodal

- Codellama 70b Instruct: —
- GPT-4.5: 37.6 (#71)

| Benchmark | Codellama 70b Instruct | GPT-4.5 |
|---|---|---|
| LMArena Vision | — | 1195 |
| VPCT | — | 45% |

## Multilingual

- Codellama 70b Instruct: 24.8 (#288)
- GPT-4.5: 52.5 (#83)

| Benchmark | Codellama 70b Instruct | GPT-4.5 |
|---|---|---|
| LMArena Non-English | 992 | 1413 |
| LMArena Chinese | — | 1421 |
| LMArena French | — | 1418 |
| LMArena German | — | 1457 |
| LMArena Japanese | — | 1416 |
| LMArena Korean | — | 1392 |
| LMArena Russian | — | 1419 |

## Instruction Following

- Codellama 70b Instruct: 51.9 (#293)
- GPT-4.5: 72.6 (#134)

| Benchmark | Codellama 70b Instruct | GPT-4.5 |
|---|---|---|
| LMArena Instruction Following | 1024 | 1404 |
| LiveBench Instruction Following | — | 72.3% |

## Long Context

- Codellama 70b Instruct: —
- GPT-4.5: 40.4 (#155)

| Benchmark | Codellama 70b Instruct | GPT-4.5 |
|---|---|---|
| Fiction.LiveBench | — | 63.9% |
| LMArena Longer Query | — | 1406 |

## Writing & Preference

- Codellama 70b Instruct: 33.4 (#277)
- GPT-4.5: 56.9 (#134)

| Benchmark | Codellama 70b Instruct | GPT-4.5 |
|---|---|---|
| LMArena Text | 1057 | 1417 |
| LMArena Creative Writing | — | 1394 |
| Short-Story Creative Writing | — | 75.6% |
| EQ-Bench Creative Writing | — | 1258 |
| LMArena Multi-Turn | — | 1444 |
| LiveBench Language | — | 61.5% |

## FAQ

### Is Codellama 70b Instruct better than GPT-4.5?

GPT-4.5 is the stronger model overall, scoring 37.2 to 33.7 on the Noometry Index.

### Is Codellama 70b Instruct or GPT-4.5 better for coding?

GPT-4.5 scores higher on coding benchmarks: 42.2 versus 37.6 in the Noometry coding category.

### How many benchmarks do Codellama 70b Instruct and GPT-4.5 share?

4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and GPT-4.5 has 42.