# GPT-5-Codex vs Llama 2-7B

> GPT-5-Codex is the stronger model overall, scoring 37.3 to 28.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-codex-vs-llama-2-7b
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in reasoning, where GPT-5-Codex leads 30.0 to 15.1.
- Llama 2-7B has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5-Codex | Llama 2-7B |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 37.3 | 28.6 |
| Rank | 190 | 315 |
| Context | 400K | — |
| Input $/M | $1.25 | — |
| Output $/M | $10 | — |
| Weights | Proprietary | Open |

## Coding

- GPT-5-Codex: 41.9 (#100)
- Llama 2-7B: 28.7 (#302)

| Benchmark | GPT-5-Codex | Llama 2-7B |
|---|---|---|
| WeirdML | 54.5% | — |
| LMArena Coding | — | 1002 |

## Agentic & Tool Use

- GPT-5-Codex: 30.8 (#66)
- Llama 2-7B: —

| Benchmark | GPT-5-Codex | Llama 2-7B |
|---|---|---|
| Terminal-Bench | 44.3% | — |

## Reasoning

- GPT-5-Codex: 30.0 (#80)
- Llama 2-7B: 15.1 (#309)

| Benchmark | GPT-5-Codex | Llama 2-7B |
|---|---|---|
| Kagi LLM Benchmark | 70.3% | — |
| Chess Puzzles | — | 0% |
| LMArena Hard Prompts | — | 1009 |
| BIG-Bench Hard | — | 39.2% |
| Epoch Capabilities Index | — | 98.54 |
| HellaSwag | — | 77.2% |
| LAMBADA | — | 73.3% |
| PIQA | — | 78.8% |
| WinoGrande | — | 69.2% |

## Math

- GPT-5-Codex: —
- Llama 2-7B: 28.2 (#231)

| Benchmark | GPT-5-Codex | Llama 2-7B |
|---|---|---|
| LMArena Math | — | 1042 |
| GSM8K | — | 16.7% |

## Knowledge

- GPT-5-Codex: —
- Llama 2-7B: 27.7 (#243)

| Benchmark | GPT-5-Codex | Llama 2-7B |
|---|---|---|
| LMArena Expert | — | 1036 |
| ARC (AI2) Challenge | — | 45.9% |
| BoolQ | — | 77.9% |
| MMLU | — | 45.8% |
| OpenBookQA | — | 58.6% |
| TriviaQA | — | 73.7% |

## Multimodal

- GPT-5-Codex: —
- Llama 2-7B: —

| Benchmark | GPT-5-Codex | Llama 2-7B |
|---|---|---|
| ScienceQA | — | 43.1% |

## Multilingual

- GPT-5-Codex: —
- Llama 2-7B: 23.9 (#288)

| Benchmark | GPT-5-Codex | Llama 2-7B |
|---|---|---|
| LMArena Non-English | — | 973 |
| LMArena Chinese | — | 973 |
| LMArena French | — | 969 |
| LMArena German | — | 978 |
| LMArena Russian | — | 995 |
| LMArena Spanish | — | 1007 |

## Instruction Following

- GPT-5-Codex: —
- Llama 2-7B: 51.0 (#293)

| Benchmark | GPT-5-Codex | Llama 2-7B |
|---|---|---|
| LMArena Instruction Following | — | 1006 |

## Long Context

- GPT-5-Codex: —
- Llama 2-7B: 30.4 (#282)

| Benchmark | GPT-5-Codex | Llama 2-7B |
|---|---|---|
| LMArena Longer Query | — | 999 |

## Writing & Preference

- GPT-5-Codex: —
- Llama 2-7B: 28.1 (#293)

| Benchmark | GPT-5-Codex | Llama 2-7B |
|---|---|---|
| LMArena Text | — | 1053 |
| LMArena Creative Writing | — | 1033 |
| LMArena Multi-Turn | — | 1029 |

## FAQ

### Is GPT-5-Codex better than Llama 2-7B?

GPT-5-Codex is the stronger model overall, scoring 37.3 to 28.6 on the Noometry Index.

### Is GPT-5-Codex or Llama 2-7B better for coding?

GPT-5-Codex scores higher on coding benchmarks: 41.9 versus 28.7 in the Noometry coding category.

### How many benchmarks do GPT-5-Codex and Llama 2-7B share?

0 benchmarks have published results for both models. GPT-5-Codex has 3 scored results on Noometry and Llama 2-7B has 29.