Leaderboard / Model
GPT-5.2 Pro
OpenAI · Closed weights · Released Dec 11, 2025 · $21 in · $168 out per 1M tokens
n/aOverall · not enough data
Score by job
Coding
Not enough data · 0 of 5 benchmarks
Agents
Not enough data · 0 of 4 benchmarks
Reasoning
30 · rank 29 · 2 of 4 benchmarks
| Benchmark | Result | Variant | z |
|---|---|---|---|
| ARC-AGI-2 | 54.2% | gpt-5.2-pro-2025-12-11_high | -0.45 |
| SimpleBench | 57.4% | gpt-5.2-pro-2025-12-11 | -0.80 |
Math
Not enough data · 2 of 5 benchmarks
| Benchmark | Result | Variant | z |
|---|---|---|---|
| FrontierMath Tiers 1–3 | 74.0% | gpt-5.2-pro-2025-12-11_xhigh | 0.41 |
| FrontierMath Tier 4 | 46.0% | gpt-5.2-pro-2025-12-11_xhigh | 0.21 |
Writing
Not enough data · 0 of 2 benchmarks
Design
Not enough data · 0 of 1 benchmarks