# GPT-5-Codex vs Mistral

> GPT-5-Codex is the stronger model overall, scoring 37.3 to 29.4 on the Noometry Index.

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

## Summary

- The widest gap is in reasoning, where GPT-5-Codex leads 30.0 to 21.3.

## Snapshot

| | GPT-5-Codex | Mistral |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 37.3 | 29.4 |
| Rank | 190 | 297 |
| Context | 400K | — |
| Input $/M | $1.25 | — |
| Output $/M | $10 | — |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-5-Codex: 41.9 (#100)
- Mistral: 33.2 (#249)

| Benchmark | GPT-5-Codex | Mistral |
|---|---|---|
| WeirdML | 54.5% | — |
| LMArena Coding | — | 1162 |

## Agentic & Tool Use

- GPT-5-Codex: 30.8 (#66)
- Mistral: —

| Benchmark | GPT-5-Codex | Mistral |
|---|---|---|
| Terminal-Bench | 44.3% | — |

## Reasoning

- GPT-5-Codex: 30.0 (#80)
- Mistral: 21.3 (#199)

| Benchmark | GPT-5-Codex | Mistral |
|---|---|---|
| Kagi LLM Benchmark | 70.3% | — |
| LMArena Hard Prompts | — | 1149 |

## Math

- GPT-5-Codex: —
- Mistral: 20.5 (#275)

| Benchmark | GPT-5-Codex | Mistral |
|---|---|---|
| Omni-MATH | — | 7.2% |
| LMArena Math | — | 1180 |

## Knowledge

- GPT-5-Codex: —
- Mistral: 16.3 (#283)

| Benchmark | GPT-5-Codex | Mistral |
|---|---|---|
| MMLU-Pro | — | 27.7% |
| GPQA (HELM) | — | 30.3% |
| LMArena Expert | — | 1125 |

## Multilingual

- GPT-5-Codex: —
- Mistral: 33.0 (#249)

| Benchmark | GPT-5-Codex | Mistral |
|---|---|---|
| LMArena Non-English | — | 1129 |
| LMArena Chinese | — | 1109 |
| LMArena French | — | 1179 |
| LMArena German | — | 1155 |
| LMArena Japanese | — | 1012 |
| LMArena Korean | — | 1032 |
| LMArena Russian | — | 1168 |
| LMArena Spanish | — | 1143 |

## Instruction Following

- GPT-5-Codex: —
- Mistral: 52.9 (#283)

| Benchmark | GPT-5-Codex | Mistral |
|---|---|---|
| IFEval | — | 56.8% |
| LMArena Instruction Following | — | 1152 |

## Long Context

- GPT-5-Codex: —
- Mistral: 35.0 (#240)

| Benchmark | GPT-5-Codex | Mistral |
|---|---|---|
| LMArena Longer Query | — | 1154 |

## Writing & Preference

- GPT-5-Codex: —
- Mistral: 37.2 (#255)

| Benchmark | GPT-5-Codex | Mistral |
|---|---|---|
| LMArena Text | — | 1165 |
| LMArena Creative Writing | — | 1158 |
| WildBench | — | 66% |
| LMArena Multi-Turn | — | 1147 |

## FAQ

### Is GPT-5-Codex better than Mistral?

GPT-5-Codex is the stronger model overall, scoring 37.3 to 29.4 on the Noometry Index.

### Is GPT-5-Codex or Mistral better for coding?

GPT-5-Codex scores higher on coding benchmarks: 41.9 versus 33.2 in the Noometry coding category.

### How many benchmarks do GPT-5-Codex and Mistral share?

0 benchmarks have published results for both models. GPT-5-Codex has 3 scored results on Noometry and Mistral has 22.