# GPT-5.3 Codex vs Llama 13b

> GPT-5.3 Codex is the stronger model overall, scoring 45.5 to 23.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-3-codex-vs-llama-13b
- Last updated: 2026-10-10
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. GPT-5.3 Codex scores higher in 1 category and Llama 13b in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where GPT-5.3 Codex leads 48.5 to 20.9.
- Llama 13b has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5.3 Codex | Llama 13b |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 45.5 | 23.9 |
| Rank | 61 | 344 |
| Context | 400K | — |
| Input $/M | $1.75 | — |
| Output $/M | $14 | — |
| Weights | Proprietary | Open |

## Coding

- GPT-5.3 Codex: 48.5 (#51)
- Llama 13b: 20.9 (#332)

| Benchmark | GPT-5.3 Codex | Llama 13b |
|---|---|---|
| SWE-bench Verified | 74.8% | — |
| LMArena WebDev | 1408 | — |
| WeirdML | 79.3% | — |
| LMArena Coding | — | 683 |
| ALE-Bench | 1,655 | — |

## Agentic & Tool Use

- GPT-5.3 Codex: 47.8 (#9)
- Llama 13b: —

| Benchmark | GPT-5.3 Codex | Llama 13b |
|---|---|---|
| Terminal-Bench | 78.4% | — |
| METR Time Horizons | 74.5% | — |
| Vending-Bench 2 | 5,940 | — |

## Reasoning

- GPT-5.3 Codex: —
- Llama 13b: 13.4 (#327)

| Benchmark | GPT-5.3 Codex | Llama 13b |
|---|---|---|
| Epoch Capabilities Index | 156.84 | 100.09 |
| LMArena Hard Prompts | — | 728 |
| BIG-Bench Hard | — | 37.9% |
| HellaSwag | — | 79.2% |
| LAMBADA | — | 75.2% |
| PIQA | — | 80.1% |
| WinoGrande | — | 73% |

## Math

- GPT-5.3 Codex: —
- Llama 13b: 24.4 (#259)

| Benchmark | GPT-5.3 Codex | Llama 13b |
|---|---|---|
| LMArena Math | — | 838 |
| GSM8K | — | 20.6% |

## Knowledge

- GPT-5.3 Codex: —
- Llama 13b: —

| Benchmark | GPT-5.3 Codex | Llama 13b |
|---|---|---|
| ARC (AI2) Challenge | — | 52.7% |
| BoolQ | — | 78.7% |
| MMLU | — | 47.7% |
| OpenBookQA | — | 56.4% |
| TriviaQA | — | 77.9% |

## Multimodal

- GPT-5.3 Codex: —
- Llama 13b: —

| Benchmark | GPT-5.3 Codex | Llama 13b |
|---|---|---|
| ScienceQA | — | 43.3% |

## Multilingual

- GPT-5.3 Codex: —
- Llama 13b: 16.8 (#292)

| Benchmark | GPT-5.3 Codex | Llama 13b |
|---|---|---|
| LMArena Non-English | — | 819 |

## Instruction Following

- GPT-5.3 Codex: —
- Llama 13b: 36.9 (#300)

| Benchmark | GPT-5.3 Codex | Llama 13b |
|---|---|---|
| LMArena Instruction Following | — | 781 |

## Writing & Preference

- GPT-5.3 Codex: —
- Llama 13b: 13.9 (#307)

| Benchmark | GPT-5.3 Codex | Llama 13b |
|---|---|---|
| LMArena Text | — | 834 |
| LMArena Creative Writing | — | 794 |
| LMArena Multi-Turn | — | 753 |

## FAQ

### Is GPT-5.3 Codex better than Llama 13b?

GPT-5.3 Codex is the stronger model overall, scoring 45.5 to 23.9 on the Noometry Index.

### Is GPT-5.3 Codex or Llama 13b better for coding?

GPT-5.3 Codex scores higher on coding benchmarks: 48.5 versus 20.9 in the Noometry coding category.

### How many benchmarks do GPT-5.3 Codex and Llama 13b share?

1 benchmark has published results for both models. GPT-5.3 Codex has 8 scored results on Noometry and Llama 13b has 21.