Benchfolio

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

BenchmarkResultVariantz
ARC-AGI-254.2%gpt-5.2-pro-2025-12-11_high-0.45
SimpleBench57.4%gpt-5.2-pro-2025-12-11-0.80

Math

Not enough data · 2 of 5 benchmarks

BenchmarkResultVariantz
FrontierMath Tiers 1–374.0%gpt-5.2-pro-2025-12-11_xhigh0.41
FrontierMath Tier 446.0%gpt-5.2-pro-2025-12-11_xhigh0.21

Writing

Not enough data · 0 of 2 benchmarks

Design

Not enough data · 0 of 1 benchmarks