# GPT-5.3 Codex vs Ministral 3B

> GPT-5.3 Codex is the stronger model overall, scoring 45.5 to 25.6 on the Noometry Index. Ministral 3B costs 120× less per token, which makes it the better buy when GPT-5.3 Codex's lead doesn't matter for your workload.

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

## Summary

- They share 1 benchmark with published results for both.
- Ministral 3B is cheaper at $0.04 / $0.04 per million input/output tokens, against $1.75 / $14 for GPT-5.3 Codex.
- GPT-5.3 Codex accepts more context: 400K tokens versus 128K.
- Ministral 3B has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5.3 Codex | Ministral 3B |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 45.5 | 25.6 |
| Rank | 61 | 336 |
| Context | 400K | 128K |
| Input $/M | $1.75 | $0.04 |
| Output $/M | $14 | $0.04 |
| Weights | Proprietary | Open |

## Coding

- GPT-5.3 Codex: 48.5 (#51)
- Ministral 3B: —

| Benchmark | GPT-5.3 Codex | Ministral 3B |
|---|---|---|
| SWE-bench Verified | 74.8% | — |
| LMArena WebDev | 1408 | — |
| WeirdML | 79.3% | — |
| ALE-Bench | 1,655 | — |

## Agentic & Tool Use

- GPT-5.3 Codex: 47.8 (#9)
- Ministral 3B: —

| Benchmark | GPT-5.3 Codex | Ministral 3B |
|---|---|---|
| Terminal-Bench | 78.4% | — |
| METR Time Horizons | 74.5% | — |
| Vending-Bench 2 | 5,940 | — |

## Reasoning

- GPT-5.3 Codex: —
- Ministral 3B: 17.7 (#278)

| Benchmark | GPT-5.3 Codex | Ministral 3B |
|---|---|---|
| Epoch Capabilities Index | 156.84 | 118.08 |
| DTBench | — | 51.7% |
| LMCA | — | 5.5% |

## Math

- GPT-5.3 Codex: —
- Ministral 3B: 24.5 (#257)

| Benchmark | GPT-5.3 Codex | Ministral 3B |
|---|---|---|
| MATH Level 5 | — | 14.4% |

## Knowledge

- GPT-5.3 Codex: —
- Ministral 3B: 10.4 (#297)

| Benchmark | GPT-5.3 Codex | Ministral 3B |
|---|---|---|
| GPQA Diamond | — | 25.3% |
| Vectara Hallucination Rate | — | 7.3% |

## FAQ

### Is GPT-5.3 Codex better than Ministral 3B?

GPT-5.3 Codex is the stronger model overall, scoring 45.5 to 25.6 on the Noometry Index. Ministral 3B costs 120× less per token, which makes it the better buy when GPT-5.3 Codex's lead doesn't matter for your workload.

### Which is cheaper, GPT-5.3 Codex or Ministral 3B?

Ministral 3B is cheaper. It lists at $0.04 per million input tokens and $0.04 per million output tokens; GPT-5.3 Codex lists at $1.75 and $14.

### Which has the bigger context window?

GPT-5.3 Codex does, with 400K tokens against 128K.

### How many benchmarks do GPT-5.3 Codex and Ministral 3B share?

1 benchmark has published results for both models. GPT-5.3 Codex has 8 scored results on Noometry and Ministral 3B has 6.