# GPT-5.2 Pro vs Magistral Small

> GPT-5.2 Pro is the stronger model overall, scoring 52.2 to 29.9 on the Noometry Index. Magistral Small costs 77× less per token, which makes it the better buy when GPT-5.2 Pro's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gpt-5-2-pro-vs-magistral-small
- Last updated: 2026-10-10
- Shared benchmarks: 3

## Summary

- They share 3 benchmarks with published results for both. GPT-5.2 Pro scores higher in 2 categories and Magistral Small in 0 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.2 Pro leads 51.8 to 6.9.
- The biggest single-benchmark swing is ARC-AGI-1: 90.5% for GPT-5.2 Pro and 5% for Magistral Small.
- Magistral Small is cheaper at $0.50 / $1.50 per million input/output tokens, against $21 / $168 for GPT-5.2 Pro.
- GPT-5.2 Pro accepts more context: 400K tokens versus 128K.
- Magistral Small has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5.2 Pro | Magistral Small |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 52.2 | 29.9 |
| Rank | 34 | 289 |
| Context | 400K | 128K |
| Input $/M | $21 | $0.50 |
| Output $/M | $168 | $1.50 |
| Weights | Proprietary | Open |

## Coding

- GPT-5.2 Pro: —
- Magistral Small: 37.8 (#172)

| Benchmark | GPT-5.2 Pro | Magistral Small |
|---|---|---|
| SciCode | — | 35.2% |

## Reasoning

- GPT-5.2 Pro: 51.8 (#31)
- Magistral Small: 6.9 (#345)

| Benchmark | GPT-5.2 Pro | Magistral Small |
|---|---|---|
| ARC-AGI-2 | 54.2% | 0% |
| ARC-AGI-1 | 90.5% | 5% |
| Epoch Capabilities Index | 155.41 | 133.19 |
| SimpleBench | 57.4% | — |
| Kagi LLM Benchmark | — | 6.3% |
| NYT Connections (extended) | 79.3% | — |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 3% |
| DTBench | — | 61.3% |

## Math

- GPT-5.2 Pro: 64.8 (#23)
- Magistral Small: 24.9 (#253)

| Benchmark | GPT-5.2 Pro | Magistral Small |
|---|---|---|
| FrontierMath (Tiers 1-3) | 74% | — |
| FrontierMath Tier 4 | 46% | — |
| OTIS Mock AIME 2024-2025 | — | 30% |
| FrontierMath Tier 4 (v1) | 31.3% | — |

## Knowledge

- GPT-5.2 Pro: —
- Magistral Small: 30.9 (#215)

| Benchmark | GPT-5.2 Pro | Magistral Small |
|---|---|---|
| GPQA Diamond | — | 56.1% |

## FAQ

### Is GPT-5.2 Pro better than Magistral Small?

GPT-5.2 Pro is the stronger model overall, scoring 52.2 to 29.9 on the Noometry Index. Magistral Small costs 77× less per token, which makes it the better buy when GPT-5.2 Pro's lead doesn't matter for your workload.

### Which is cheaper, GPT-5.2 Pro or Magistral Small?

Magistral Small is cheaper. It lists at $0.50 per million input tokens and $1.50 per million output tokens; GPT-5.2 Pro lists at $21 and $168.

### Which has the bigger context window?

GPT-5.2 Pro does, with 400K tokens against 128K.

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

3 benchmarks have published results for both models. GPT-5.2 Pro has 8 scored results on Noometry and Magistral Small has 10.