# GPT-5.2 Pro vs o1-mini

> GPT-5.2 Pro is the stronger model overall, scoring 52.2 to 33.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-2-pro-vs-o1-mini
- Last updated: 2026-10-10
- Shared benchmarks: 4

## Summary

- They share 4 benchmarks with published results for both. GPT-5.2 Pro scores higher in 2 categories and o1-mini 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 8.9.
- The biggest single-benchmark swing is ARC-AGI-1: 90.5% for GPT-5.2 Pro and 14% for o1-mini.

## Snapshot

| | GPT-5.2 Pro | o1-mini |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 52.2 | 33.7 |
| Rank | 34 | 230 |
| Context | 400K | — |
| Input $/M | $21 | — |
| Output $/M | $168 | — |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-5.2 Pro: —
- o1-mini: 35.1 (#218)

| Benchmark | GPT-5.2 Pro | o1-mini |
|---|---|---|
| Aider Polyglot | — | 32.9% |
| WeirdML | — | 36.3% |
| LiveBench Coding | — | 48% |
| LMArena Coding | — | 1362 |
| HumanEval+ | — | 89% |
| MBPP+ | — | 78.8% |

## Agentic & Tool Use

- GPT-5.2 Pro: —
- o1-mini: 24.3 (#112)

| Benchmark | GPT-5.2 Pro | o1-mini |
|---|---|---|
| Cybench | — | 10% |

## Reasoning

- GPT-5.2 Pro: 51.8 (#31)
- o1-mini: 8.9 (#340)

| Benchmark | GPT-5.2 Pro | o1-mini |
|---|---|---|
| ARC-AGI-2 | 54.2% | 0.8% |
| SimpleBench | 57.4% | 18.1% |
| ARC-AGI-1 | 90.5% | 14% |
| Epoch Capabilities Index | 155.41 | 135.82 |
| NYT Connections (extended) | 79.3% | — |
| LiveBench Reasoning | — | 72.3% |
| LMArena Hard Prompts | — | 1333 |
| LiveBench Data Analysis | — | 57.9% |
| LiveBench | — | 57.8% |

## Math

- GPT-5.2 Pro: 64.8 (#23)
- o1-mini: 33.7 (#168)

| Benchmark | GPT-5.2 Pro | o1-mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 74% | — |
| FrontierMath Tier 4 | 46% | — |
| OTIS Mock AIME 2024-2025 | — | 46.9% |
| LiveBench Math | — | 62% |
| LMArena Math | — | 1358 |
| MATH Level 5 | — | 89.2% |
| FrontierMath (Feb 2025 set) | — | 1.7% |
| FrontierMath Tier 4 (v1) | 31.3% | — |

## Knowledge

- GPT-5.2 Pro: —
- o1-mini: 34.8 (#180)

| Benchmark | GPT-5.2 Pro | o1-mini |
|---|---|---|
| GPQA Diamond | — | 62.4% |
| Confabulations | — | 18.6% |
| LMArena Expert | — | 1316 |

## Multilingual

- GPT-5.2 Pro: —
- o1-mini: 43.8 (#177)

| Benchmark | GPT-5.2 Pro | o1-mini |
|---|---|---|
| LMArena Non-English | — | 1289 |
| LMArena Chinese | — | 1314 |
| LMArena French | — | 1292 |
| LMArena German | — | 1278 |
| LMArena Japanese | — | 1245 |
| LMArena Korean | — | 1223 |
| LMArena Russian | — | 1283 |
| LMArena Spanish | — | 1302 |

## Instruction Following

- GPT-5.2 Pro: —
- o1-mini: 67.0 (#200)

| Benchmark | GPT-5.2 Pro | o1-mini |
|---|---|---|
| LiveBench Instruction Following | — | 65.4% |
| LMArena Instruction Following | — | 1304 |

## Long Context

- GPT-5.2 Pro: —
- o1-mini: 40.1 (#156)

| Benchmark | GPT-5.2 Pro | o1-mini |
|---|---|---|
| LMArena Longer Query | — | 1321 |

## Writing & Preference

- GPT-5.2 Pro: —
- o1-mini: 48.6 (#196)

| Benchmark | GPT-5.2 Pro | o1-mini |
|---|---|---|
| LMArena Text | — | 1317 |
| LMArena Creative Writing | — | 1244 |
| Short-Story Creative Writing | — | 64.9% |
| LMArena Multi-Turn | — | 1314 |
| LiveBench Language | — | 40.9% |

## FAQ

### Is GPT-5.2 Pro better than o1-mini?

GPT-5.2 Pro is the stronger model overall, scoring 52.2 to 33.7 on the Noometry Index.

### How many benchmarks do GPT-5.2 Pro and o1-mini share?

4 benchmarks have published results for both models. GPT-5.2 Pro has 8 scored results on Noometry and o1-mini has 39.