# GPT-5.2 vs o3-pro

> GPT-5.2 is the stronger model overall, scoring 54.1 to 42.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-2-vs-o3-pro
- Last updated: 2026-10-10
- Shared benchmarks: 8

## Summary

- They share 8 benchmarks with published results for both. GPT-5.2 scores higher in 3 categories and o3-pro in 2 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5.2 leads 59.2 to 29.0.
- The biggest single-benchmark swing is ARC-AGI-2: 52.9% for GPT-5.2 and 4.9% for o3-pro.
- GPT-5.2 is cheaper at $1.75 / $14 per million input/output tokens, against $20 / $80 for o3-pro.
- GPT-5.2 accepts more context: 400K tokens versus 200K.

## Snapshot

| | GPT-5.2 | o3-pro |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 54.1 | 42.7 |
| Rank | 31 | 94 |
| Context | 400K | 200K |
| Input $/M | $1.75 | $20 |
| Output $/M | $14 | $80 |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-5.2: 52.2 (#32)
- o3-pro: 55.1 (#22)

| Benchmark | GPT-5.2 | o3-pro |
|---|---|---|
| WeirdML | 72.2% | 58.2% |
| SWE-bench Verified | 73.8% | — |
| SWE-bench Verified (bash only) | 72.8% | — |
| Aider Polyglot | — | 84.9% |
| LMArena WebDev | 1415 | — |
| SWE-bench Multilingual | 66.7% | — |
| GSO | 27.4% | — |
| LMArena Coding | 1447 | — |
| ALE-Bench | 1,294 | — |
| AlgoTune | 2.05 | — |

## Agentic & Tool Use

- GPT-5.2: 40.0 (#24)
- o3-pro: —

| Benchmark | GPT-5.2 | o3-pro |
|---|---|---|
| Terminal-Bench | 64.9% | — |
| Berkeley Function Calling Leaderboard | 55.9% | — |
| GDPval | 49.7% | — |
| Remote Labor Index | 2.5% | — |
| τ²-bench Airline | 83% | — |
| τ²-bench Banking | 32.2% | — |
| τ²-bench Retail | 81.6% | — |
| τ²-bench Telecom | 89.7% | — |
| DeepResearch Bench | 41.1% | — |
| LMArena Search | 1207 | — |
| METR Time Horizons | 75.3% | — |
| Vending-Bench 2 | 3,591 | — |

## Reasoning

- GPT-5.2: 50.1 (#33)
- o3-pro: 24.1 (#152)

| Benchmark | GPT-5.2 | o3-pro |
|---|---|---|
| ARC-AGI-2 | 52.9% | 4.9% |
| Kagi LLM Benchmark | 73.3% | 72.1% |
| ARC-AGI-1 | 86.2% | 59.3% |
| DTBench | 90.9% | 86.9% |
| LMCA | 43.9% | 38.5% |
| Epoch Capabilities Index | 153.45 | 147.43 |
| SimpleBench | 45.8% | — |
| NYT Connections (extended) | 83.6% | — |
| Chess Puzzles | 49% | — |
| EnigmaEval | 10.4% | — |
| EBR-Bench | 23% | — |
| LMArena Hard Prompts | 1445 | — |
| Mystery Game Puzzles | 23% | — |
| ForecastBench | 60.1 | — |

## Math

- GPT-5.2: 59.8 (#32)
- o3-pro: —

| Benchmark | GPT-5.2 | o3-pro |
|---|---|---|
| FrontierMath (Tiers 1-3) | 67.4% | — |
| FrontierMath Tier 4 | 31.7% | — |
| MathArena Final-Answer Competitions | 72% | — |
| OTIS Mock AIME 2024-2025 | 96.1% | — |
| ProofBench | 15% | — |
| LMArena Math | 1439 | — |
| FrontierMath (Feb 2025 set) | 40.7% | — |
| FrontierMath Tier 4 (v1) | 18.8% | — |

## Knowledge

- GPT-5.2: 59.2 (#29)
- o3-pro: 29.0 (#234)

| Benchmark | GPT-5.2 | o3-pro |
|---|---|---|
| Vectara Hallucination Rate | 8.4% | 23.3% |
| GPQA Diamond | 91.4% | — |
| Humanity's Last Exam | 27.8% | — |
| SimpleQA Verified | 37.1% | — |
| Confabulations | — | 14.2% |
| LMArena Expert | 1445 | — |

## Multimodal

- GPT-5.2: 50.9 (#7)
- o3-pro: —

| Benchmark | GPT-5.2 | o3-pro |
|---|---|---|
| LMArena Vision | 1268 | — |
| VPCT | 84% | — |
| Furniture Assembly | 38.3% | — |
| LMArena Document | 1405 | — |

## Multilingual

- GPT-5.2: 53.6 (#63)
- o3-pro: —

| Benchmark | GPT-5.2 | o3-pro |
|---|---|---|
| LMArena Non-English | 1425 | — |
| LMArena Chinese | 1460 | — |
| LMArena French | 1456 | — |
| LMArena German | 1448 | — |
| LMArena Japanese | 1421 | — |
| LMArena Korean | 1390 | — |
| LMArena Russian | 1440 | — |
| LMArena Spanish | 1433 | — |

## Instruction Following

- GPT-5.2: 74.9 (#83)
- o3-pro: —

| Benchmark | GPT-5.2 | o3-pro |
|---|---|---|
| LMArena Instruction Following | 1417 | — |

## Long Context

- GPT-5.2: 44.0 (#74)
- o3-pro: 72.1 (#1)

| Benchmark | GPT-5.2 | o3-pro |
|---|---|---|
| Fiction.LiveBench | — | 97.2% |
| CL-bench | 18.2% | — |
| LMArena Longer Query | 1428 | — |

## Writing & Preference

- GPT-5.2: 67.0 (#30)
- o3-pro: 57.1 (#128)

| Benchmark | GPT-5.2 | o3-pro |
|---|---|---|
| LMArena Text | 1439 | — |
| LMArena Creative Writing | 1402 | — |
| Short-Story Creative Writing | — | 84.4% |
| EQ-Bench Creative Writing | 1703 | — |
| LMArena Multi-Turn | 1458 | — |

## FAQ

### Is GPT-5.2 better than o3-pro?

GPT-5.2 is the stronger model overall, scoring 54.1 to 42.7 on the Noometry Index.

### Which is cheaper, GPT-5.2 or o3-pro?

GPT-5.2 is cheaper. It lists at $1.75 per million input tokens and $14 per million output tokens; o3-pro lists at $20 and $80.

### Is GPT-5.2 or o3-pro better for coding?

o3-pro scores higher on coding benchmarks: 55.1 versus 52.2 in the Noometry coding category.

### Which has the bigger context window?

GPT-5.2 does, with 400K tokens against 200K.

### How many benchmarks do GPT-5.2 and o3-pro share?

8 benchmarks have published results for both models. GPT-5.2 has 67 scored results on Noometry and o3-pro has 12.