GPT-5.2 ProvsGPT-5-Pro
Across 5 shared benchmarks, GPT-5.2 Pro leads overall: GPT-5.2 Pro wins 5, GPT-5-Pro wins 0, with 0 ties and an average score difference of +17.
GPT-5.2 Pro
OpenAI · 2025-12-11 · Reasoning model
GPT-5-Pro
OpenAI · 2025-08-07 · Reasoning model
GPT-5.2 Pro5 wins(100%)(0%)0 winsGPT-5-Pro
Benchmark scores
Grouped by capability, sorted by largest gap within each. 5 shared benchmarks.
General Knowledge
GPT-5.2 Pro 4/4| Benchmark | GPT-5.2 Pro | GPT-5-Pro | Diff |
|---|---|---|---|
| ARC-AGI-2 | 54.2020 / 59 | 1832 / 59 | +36.20 |
| ARC-AGI | 90.5015 / 65 | 70.2027 / 65 | +20.30 |
| HLE | 5022 / 157 | 4245 / 157 | +8 |
| GPQA Diamond | 93.208 / 178 | 89.4023 / 178 | +3.80 |
Math and Reasoning
GPT-5.2 Pro 1/1| Benchmark | GPT-5.2 Pro | GPT-5-Pro | Diff |
|---|---|---|---|
| FrontierMath - Tier 4 | 31.309 / 80 | 14.6023 / 80 | +16.70 |
Specs
| Field | GPT-5.2 Pro | GPT-5-Pro |
|---|---|---|
| Publisher | OpenAI | OpenAI |
| Release date | 2025-12-11 | 2025-08-07 |
| Model type | Reasoning model | Reasoning model |
| Architecture | Dense | Dense |
| Parameters | Not available | Not available |
| Context length | 256K | 400K |
| Max output | Not available | 125K |
Summary
- GPT-5.2 Proleads in:General Knowledge (4/4), Math and Reasoning (1/1)
On average across the 5 shared benchmarks, GPT-5.2 Pro scores 17 higher.
Largest single-benchmark gap: ARC-AGI-2 — GPT-5.2 Pro 54.20 vs GPT-5-Pro 18 (+36.20).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.