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 Microsoft, OpenAI, Google DeepMind and 7 more, by GPQA Diamond.
Create it free
Takes a free account
Microsoft
Adversarial Nli
0.58 %
BALROG
0.12 %
Bbh
0.81 %
Bool Q
0.85 %
Chess Puzzles
0.01 %
GPQA Diamond
0.56 %
Gsm8k
0.89 %
Hella Swag
0.82 %
Lambada
0.87 %
Lech Mazur Writing
0.06 %
Live bench
0.42 %
Math Level 5
0.65 %
Mmlu
0.85 %
Open Book Qa
0.88 %
OTIS Mock AIME 2024 2025
0.14 %
Piqa
0.89 %
SciCode
0.11 %
Science Qa
0.91 %
Trivia Qa
0.74 %
Wino Grande
0.82 %
Training Compute
932,020,150,000.00T FLOP
Microsoft benchmark results over time.