# GPT-5.2 Pro vs Mistral

> GPT-5.2 Pro is the stronger model overall, scoring 52.3 to 29.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-2-pro-vs-mistral
- Last updated: 2026-10-12
- Shared benchmarks: 0

## Summary

- The widest gap is in math, where GPT-5.2 Pro leads 65.3 to 22.3.

## Snapshot

| | GPT-5.2 Pro | Mistral |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 52.3 | 29.9 |
| Rank | 39 | 303 |
| Context | 400K | — |
| Input $/M | $21 | — |
| Output $/M | $168 | — |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-5.2 Pro: —
- Mistral: 33.8 (#250)

| Benchmark | GPT-5.2 Pro | Mistral |
|---|---|---|
| LMArena Coding | — | 1162 |

## Reasoning

- GPT-5.2 Pro: 51.5 (#33)
- Mistral: 22.2 (#200)

| Benchmark | GPT-5.2 Pro | Mistral |
|---|---|---|
| ARC-AGI-2 | 54.2% | — |
| SimpleBench | 57.4% | — |
| NYT Connections (extended) | 79.3% | — |
| ARC-AGI-1 | 90.5% | — |
| LMArena Hard Prompts | — | 1149 |
| Epoch Capabilities Index | 155.4 | — |

## Math

- GPT-5.2 Pro: 65.3 (#29)
- Mistral: 22.3 (#278)

| Benchmark | GPT-5.2 Pro | Mistral |
|---|---|---|
| FrontierMath (Tiers 1-3) | 74% | — |
| FrontierMath Tier 4 | 46% | — |
| Omni-MATH | — | 7.2% |
| LMArena Math | — | 1180 |
| FrontierMath Tier 4 (v1) | 31.3% | — |

## Knowledge

- GPT-5.2 Pro: —
- Mistral: 16.6 (#288)

| Benchmark | GPT-5.2 Pro | Mistral |
|---|---|---|
| MMLU-Pro | — | 27.7% |
| GPQA (HELM) | — | 30.3% |
| LMArena Expert | — | 1125 |

## Multilingual

- GPT-5.2 Pro: —
- Mistral: 32.8 (#254)

| Benchmark | GPT-5.2 Pro | Mistral |
|---|---|---|
| LMArena Non-English | — | 1129 |
| LMArena Chinese | — | 1109 |
| LMArena French | — | 1180 |
| LMArena German | — | 1155 |
| LMArena Japanese | — | 1013 |
| LMArena Korean | — | 1032 |
| LMArena Russian | — | 1168 |
| LMArena Spanish | — | 1143 |

## Instruction Following

- GPT-5.2 Pro: —
- Mistral: 52.6 (#288)

| Benchmark | GPT-5.2 Pro | Mistral |
|---|---|---|
| IFEval | — | 56.8% |
| LMArena Instruction Following | — | 1152 |

## Long Context

- GPT-5.2 Pro: —
- Mistral: 35.0 (#245)

| Benchmark | GPT-5.2 Pro | Mistral |
|---|---|---|
| LMArena Longer Query | — | 1153 |

## Writing & Preference

- GPT-5.2 Pro: —
- Mistral: 37.0 (#260)

| Benchmark | GPT-5.2 Pro | Mistral |
|---|---|---|
| LMArena Text | — | 1165 |
| LMArena Creative Writing | — | 1158 |
| WildBench | — | 66% |
| LMArena Multi-Turn | — | 1147 |

## FAQ

### Is GPT-5.2 Pro better than Mistral?

GPT-5.2 Pro is the stronger model overall, scoring 52.3 to 29.9 on the Noometry Index.

### How many benchmarks do GPT-5.2 Pro and Mistral share?

0 benchmarks have published results for both models. GPT-5.2 Pro has 8 scored results on Noometry and Mistral has 22.