GPT-5.2 Pro (2025-12-11): benchmark results
Provider: OpenAI. Released 2025-12-11. Access: API.
Aggregate Rating 1767 ± 9, rank #147 of 10916 rated models, from 5 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Chess Puzzles (Epoch AI) | 60 | Accuracy (%) | 95 |
| FrontierMath - Tiers 1-3 (v2) | 74 | Accuracy (%, 285 private v2 problems) | 82.3 |
| FrontierMath - Tier 4 (v2) | 46 | Accuracy (%, 41 private v2 problems) | 63 |
| SEAL - Professional Reasoning Benchmark - Finance | 46.34 | Score | 57.1 |
| SEAL - Professional Reasoning Benchmark - Legal | 45.44 | Score | 55.3 |
Interactive version: theaggregate.ai/model?slug=gpt-5-2-pro-2025-12-11 · How It Works · Data refreshed daily, snapshot 2026-11-08.