Benchfolio

Leaderboard / Model

GPT-5.4 Pro

OpenAI · Closed weights · Released Mar 5, 2026 · $30 in · $180 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

77 · rank 8 · 4 of 4 benchmarks

BenchmarkResultVariantz
GPQA Diamond94.6%gpt-5.4-pro-2026-03-05_xhigh1.23
ARC-AGI-283.3%gpt-5.4-pro-2026-03-05_xhigh0.89
SimpleBench74.1%gpt-5.4-pro-2026-03-05_unknown0.87
Humanity’s Last Exam44.3%gpt-5.4-pro-2026-03-05_unknown0.75

Math

Not enough data · 2 of 5 benchmarks

BenchmarkResultVariantz
FrontierMath Tiers 1–382.5%gpt-5.4-pro-2026-03-05_xhigh1.00
FrontierMath Tier 458.5%gpt-5.4-pro-2026-03-05_xhigh0.73

Writing

Not enough data · 0 of 2 benchmarks

Design

Not enough data · 0 of 1 benchmarks