# GPT-5 vs GPT-5.2 Pro

> GPT-5.2 Pro is the stronger model overall, scoring 52.2 to 50.9 on the Noometry Index. GPT-5 costs 17× 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-vs-gpt-5-2-pro
- Last updated: 2026-10-10
- Shared benchmarks: 7

## Summary

- They share 7 benchmarks with published results for both. GPT-5 scores higher in 0 categories and GPT-5.2 Pro in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.2 Pro leads 51.8 to 38.3.
- The biggest single-benchmark swing is ARC-AGI-2: 9.9% for GPT-5 and 54.2% for GPT-5.2 Pro.
- GPT-5 is cheaper at $1.25 / $10 per million input/output tokens, against $21 / $168 for GPT-5.2 Pro.

## Snapshot

| | GPT-5 | GPT-5.2 Pro |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 50.9 | 52.2 |
| Rank | 37 | 34 |
| Context | 400K | 400K |
| Input $/M | $1.25 | $21 |
| Output $/M | $10 | $168 |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-5: 50.7 (#39)
- GPT-5.2 Pro: —

| Benchmark | GPT-5 | GPT-5.2 Pro |
|---|---|---|
| SWE-bench Verified | 73.6% | — |
| SWE-bench Verified (bash only) | 65% | — |
| Aider Polyglot | 88% | — |
| LMArena WebDev | 1417 | — |
| SciCode | 42.9% | — |
| GSO | 6.9% | — |
| WeirdML | 60.7% | — |
| LMArena Coding | 1436 | — |
| ALE-Bench | 1,162 | — |
| AlgoTune | 1.67 | — |

## Agentic & Tool Use

- GPT-5: 33.0 (#53)
- GPT-5.2 Pro: —

| Benchmark | GPT-5 | GPT-5.2 Pro |
|---|---|---|
| Terminal-Bench | 49.6% | — |
| GDPval | 34.8% | — |
| Remote Labor Index | 1.7% | — |
| DeepResearch Bench | 49.6% | — |
| BALROG | 32.8% | — |
| LMArena Search | 1133 | — |
| METR Time Horizons | 69.6% | — |

## Reasoning

- GPT-5: 38.3 (#55)
- GPT-5.2 Pro: 51.8 (#31)

| Benchmark | GPT-5 | GPT-5.2 Pro |
|---|---|---|
| ARC-AGI-2 | 9.9% | 54.2% |
| SimpleBench | 56.7% | 57.4% |
| ARC-AGI-1 | 65.7% | 90.5% |
| Epoch Capabilities Index | 150 | 155.41 |
| Kagi LLM Benchmark | 72.7% | — |
| NYT Connections (extended) | — | 79.3% |
| CritPt | 12.6% | — |
| Chess Puzzles | 37% | — |
| EnigmaEval | 10.5% | — |
| EBR-Bench | 12.7% | — |
| LMArena Hard Prompts | 1415 | — |
| Mystery Game Puzzles | 23% | — |
| DTBench | 90.7% | — |
| LMCA | 40% | — |
| ForecastBench | 61.4 | — |

## Math

- GPT-5: 54.6 (#36)
- GPT-5.2 Pro: 64.8 (#23)

| Benchmark | GPT-5 | GPT-5.2 Pro |
|---|---|---|
| FrontierMath (Tiers 1-3) | 55.4% | 74% |
| FrontierMath Tier 4 | 22% | 46% |
| FrontierMath Tier 4 (v1) | 12.5% | 31.3% |
| OTIS Mock AIME 2024-2025 | 91.4% | — |
| ProofBench | 18% | — |
| Omni-MATH | 64.7% | — |
| LMArena Math | 1406 | — |
| MATH Level 5 | 98.1% | — |
| FrontierMath (Feb 2025 set) | 32.4% | — |

## Knowledge

- GPT-5: 56.5 (#37)
- GPT-5.2 Pro: —

| Benchmark | GPT-5 | GPT-5.2 Pro |
|---|---|---|
| GPQA Diamond | 86.2% | — |
| Humanity's Last Exam | 25.3% | — |
| SimpleQA Verified | 50.1% | — |
| MMLU-Pro | 86.3% | — |
| Confabulations | 10.3% | — |
| Vectara Hallucination Rate | 14.7% | — |
| GPQA (HELM) | 79.2% | — |
| LMArena Expert | 1420 | — |

## Multimodal

- GPT-5: 46.1 (#12)
- GPT-5.2 Pro: —

| Benchmark | GPT-5 | GPT-5.2 Pro |
|---|---|---|
| LMArena Vision | 1232 | — |
| GeoBench | 81% | — |
| VPCT | 66% | — |

## Multilingual

- GPT-5: 51.5 (#105)
- GPT-5.2 Pro: —

| Benchmark | GPT-5 | GPT-5.2 Pro |
|---|---|---|
| LMArena Non-English | 1397 | — |
| LMArena Chinese | 1423 | — |
| LMArena French | 1409 | — |
| LMArena German | 1415 | — |
| LMArena Japanese | 1411 | — |
| LMArena Korean | 1361 | — |
| LMArena Russian | 1406 | — |
| LMArena Spanish | 1398 | — |

## Instruction Following

- GPT-5: 74.0 (#107)
- GPT-5.2 Pro: —

| Benchmark | GPT-5 | GPT-5.2 Pro |
|---|---|---|
| IFEval | 87.5% | — |
| LMArena Instruction Following | 1388 | — |

## Long Context

- GPT-5: 69.5 (#2)
- GPT-5.2 Pro: —

| Benchmark | GPT-5 | GPT-5.2 Pro |
|---|---|---|
| Fiction.LiveBench | 97.2% | — |
| LMArena Longer Query | 1399 | — |

## Writing & Preference

- GPT-5: 63.5 (#63)
- GPT-5.2 Pro: —

| Benchmark | GPT-5 | GPT-5.2 Pro |
|---|---|---|
| LMArena Text | 1406 | — |
| LMArena Creative Writing | 1365 | — |
| Short-Story Creative Writing | 86% | — |
| EQ-Bench Creative Writing | 1627 | — |
| WildBench | 85.7% | — |
| LMArena Multi-Turn | 1426 | — |

## FAQ

### Is GPT-5 better than GPT-5.2 Pro?

GPT-5.2 Pro is the stronger model overall, scoring 52.2 to 50.9 on the Noometry Index. GPT-5 costs 17× 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 or GPT-5.2 Pro?

GPT-5 is cheaper. It lists at $1.25 per million input tokens and $10 per million output tokens; GPT-5.2 Pro lists at $21 and $168.

### Which has the bigger context window?

Both accept 400K tokens.

### How many benchmarks do GPT-5 and GPT-5.2 Pro share?

7 benchmarks have published results for both models. GPT-5 has 69 scored results on Noometry and GPT-5.2 Pro has 8.