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-3.1-8B-Instruct, gemini-4-argon_high, gpt-6-astra_max and 7 more, by GPQA Diamond.
Create it free
Takes a free account
Llama-3.1-8B-Instruct
BALROG
15 %
Bool Q
83 %
Dtbench
51 %
GPQA Diamond
27 %
Gsm8k
82 %
Lmca
5 %
Math Level 5
23 %
Mmlu
56 %
OTIS Mock AIME 2024 2025
2 %
Piqa
81 %
SciCode
13 %
WeirdML
2 %
Training Compute
1,224,000,000,000.00T FLOP
Llama-3.1-8B-Instruct benchmark results.