# Codellama 70b Instruct vs GPT-5-Codex

> GPT-5-Codex is the stronger model overall, scoring 37.3 to 33.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codellama-70b-instruct-vs-gpt-5-codex
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in reasoning, where GPT-5-Codex leads 30.0 to 19.2.
- Codellama 70b Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | Codellama 70b Instruct | GPT-5-Codex |
|---|---|---|
| Provider | Meta | OpenAI |
| Noometry Index | 33.3 | 37.3 |
| Rank | 236 | 190 |
| Context | — | 400K |
| Input $/M | — | $1.25 |
| Output $/M | — | $10 |
| Weights | Open | Proprietary |

## Coding

- Codellama 70b Instruct: 37.0 (#189)
- GPT-5-Codex: 41.9 (#100)

| Benchmark | Codellama 70b Instruct | GPT-5-Codex |
|---|---|---|
| WeirdML | — | 54.5% |
| BigCodeBench Instruct | 40.7% | — |
| BigCodeBench Complete | 49.6% | — |
| HumanEval+ | 65.9% | — |

## Agentic & Tool Use

- Codellama 70b Instruct: —
- GPT-5-Codex: 30.8 (#66)

| Benchmark | Codellama 70b Instruct | GPT-5-Codex |
|---|---|---|
| Terminal-Bench | — | 44.3% |

## Reasoning

- Codellama 70b Instruct: 19.2 (#241)
- GPT-5-Codex: 30.0 (#80)

| Benchmark | Codellama 70b Instruct | GPT-5-Codex |
|---|---|---|
| Kagi LLM Benchmark | — | 70.3% |
| LMArena Hard Prompts | 1052 | — |

## Multilingual

- Codellama 70b Instruct: 24.9 (#283)
- GPT-5-Codex: —

| Benchmark | Codellama 70b Instruct | GPT-5-Codex |
|---|---|---|
| LMArena Non-English | 992 | — |

## Instruction Following

- Codellama 70b Instruct: 52.1 (#288)
- GPT-5-Codex: —

| Benchmark | Codellama 70b Instruct | GPT-5-Codex |
|---|---|---|
| LMArena Instruction Following | 1024 | — |

## Writing & Preference

- Codellama 70b Instruct: 33.6 (#272)
- GPT-5-Codex: —

| Benchmark | Codellama 70b Instruct | GPT-5-Codex |
|---|---|---|
| LMArena Text | 1057 | — |

## FAQ

### Is Codellama 70b Instruct better than GPT-5-Codex?

GPT-5-Codex is the stronger model overall, scoring 37.3 to 33.3 on the Noometry Index.

### Is Codellama 70b Instruct or GPT-5-Codex better for coding?

GPT-5-Codex scores higher on coding benchmarks: 41.9 versus 37.0 in the Noometry coding category.

### How many benchmarks do Codellama 70b Instruct and GPT-5-Codex share?

0 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and GPT-5-Codex has 3.