ixio
← Leaderboard
model profile
Excellent

GPT-5.4 Pro

OpenAI·gpt-5-4-pro
Rank · overall#7
Score86.8

Benchmark scores

3 benchmarks
FrontierMath (Tier 4)58.5%
Accuracy · ± 7.8
MathArena Apex69.8%
Accuracy
BrowseComp89.3%
Accuracy

Across harnesses

0 agents

This model appears only in model-level benchmarks — no harness ran it directly.

Scraped and aggregated from public leaderboards · 2026-07-22