# GPT-5-Codex vs Llama 3.2 3B

> GPT-5-Codex is the stronger model overall, scoring 37.9 to 28.9 on the Noometry Index. Llama 3.2 3B costs 29× less per token, which makes it the better buy when GPT-5-Codex's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gpt-5-codex-vs-llama-3-2-3b
- Last updated: 2026-10-11
- Shared benchmarks: 0

## Summary

- The widest gap is in coding, where GPT-5-Codex leads 42.4 to 27.6.
- Llama 3.2 3B is cheaper at $0.05 / $0.33 per million input/output tokens, against $1.25 / $10 for GPT-5-Codex.
- GPT-5-Codex accepts more context: 400K tokens versus 131K.
- Llama 3.2 3B has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5-Codex | Llama 3.2 3B |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 37.9 | 28.9 |
| Rank | 192 | 321 |
| Context | 400K | 131K |
| Input $/M | $1.25 | $0.05 |
| Output $/M | $10 | $0.33 |
| Weights | Proprietary | Open |

## Coding

- GPT-5-Codex: 42.4 (#103)
- Llama 3.2 3B: 27.6 (#319)

| Benchmark | GPT-5-Codex | Llama 3.2 3B |
|---|---|---|
| WeirdML | 54.5% | — |
| BigCodeBench Instruct | — | 23.4% |
| LMArena Coding | — | 1098 |
| BigCodeBench Complete | — | 28.3% |

## Agentic & Tool Use

- GPT-5-Codex: 31.0 (#72)
- Llama 3.2 3B: 20.1 (#143)

| Benchmark | GPT-5-Codex | Llama 3.2 3B |
|---|---|---|
| Terminal-Bench | 44.3% | — |
| Berkeley Function Calling Leaderboard | — | 21.9% |
| BALROG | — | 10.1% |

## Reasoning

- GPT-5-Codex: 30.9 (#83)
- Llama 3.2 3B: 21.0 (#228)

| Benchmark | GPT-5-Codex | Llama 3.2 3B |
|---|---|---|
| Kagi LLM Benchmark | 70.3% | — |
| LMArena Hard Prompts | — | 1095 |

## Math

- GPT-5-Codex: —
- Llama 3.2 3B: 32.4 (#214)

| Benchmark | GPT-5-Codex | Llama 3.2 3B |
|---|---|---|
| LMArena Math | — | 1126 |

## Knowledge

- GPT-5-Codex: —
- Llama 3.2 3B: 29.7 (#235)

| Benchmark | GPT-5-Codex | Llama 3.2 3B |
|---|---|---|
| LMArena Expert | — | 1090 |

## Multilingual

- GPT-5-Codex: —
- Llama 3.2 3B: 26.2 (#281)

| Benchmark | GPT-5-Codex | Llama 3.2 3B |
|---|---|---|
| LMArena Non-English | — | 1019 |
| LMArena Chinese | — | 1017 |
| LMArena German | — | 1056 |
| LMArena Russian | — | 949 |

## Instruction Following

- GPT-5-Codex: —
- Llama 3.2 3B: 56.0 (#275)

| Benchmark | GPT-5-Codex | Llama 3.2 3B |
|---|---|---|
| LMArena Instruction Following | — | 1089 |

## Long Context

- GPT-5-Codex: —
- Llama 3.2 3B: 33.4 (#261)

| Benchmark | GPT-5-Codex | Llama 3.2 3B |
|---|---|---|
| LMArena Longer Query | — | 1100 |

## Writing & Preference

- GPT-5-Codex: —
- Llama 3.2 3B: 24.7 (#307)

| Benchmark | GPT-5-Codex | Llama 3.2 3B |
|---|---|---|
| LMArena Text | — | 1110 |
| LMArena Creative Writing | — | 1094 |
| EQ-Bench Creative Writing | — | 595 |
| LMArena Multi-Turn | — | 1105 |

## FAQ

### Is GPT-5-Codex better than Llama 3.2 3B?

GPT-5-Codex is the stronger model overall, scoring 37.9 to 28.9 on the Noometry Index. Llama 3.2 3B costs 29× less per token, which makes it the better buy when GPT-5-Codex's lead doesn't matter for your workload.

### Which is cheaper, GPT-5-Codex or Llama 3.2 3B?

Llama 3.2 3B is cheaper. It lists at $0.05 per million input tokens and $0.33 per million output tokens; GPT-5-Codex lists at $1.25 and $10.

### Is GPT-5-Codex or Llama 3.2 3B better for coding?

GPT-5-Codex scores higher on coding benchmarks: 42.4 versus 27.6 in the Noometry coding category.

### Which has the bigger context window?

GPT-5-Codex does, with 400K tokens against 131K.

### How many benchmarks do GPT-5-Codex and Llama 3.2 3B share?

0 benchmarks have published results for both models. GPT-5-Codex has 3 scored results on Noometry and Llama 3.2 3B has 18.