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 Llama-3.3-70B-Instruct, gemini-4-argon_high, gpt-6-astra_max and 7 more, by GPQA Diamond.
Create it free
Takes a free account
Llama-3.3-70B-Instruct
BALROG
23 %
Dtbench
59 %
Forecastbench
61 %
GPQA Diamond
47 %
Live bench
50 %
Lmca
18 %
Math Level 5
42 %
Mmlu
86 %
OTIS Mock AIME 2024 2025
5 %
SciCode
26 %
SimpleBench
20 %
WeirdML
14 %
Training Compute
6,864,976,800,000.00T FLOP
Llama-3.3-70B-Instruct benchmark results.