This website uses cookies for authentication, support chat, and analytics. Only authentication cookies are turned on by default.
Animate this data
Bar chart race of phi-4, gemini-4-argon_high, gpt-6-astra_max and 7 more, by GPQA Diamond.
Create it free
Takes a free account
phi-4
BALROG
12 %
GPQA Diamond
56 %
Lech Mazur Writing
6 %
Live bench
42 %
Math Level 5
65 %
Mmlu
85 %
OTIS Mock AIME 2024 2025
14 %
Training Compute
932,020,150,000.00T FLOP
phi-4 benchmark results.