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 StepFun, Google DeepMind, OpenAI and 7 more, by GPQA Diamond.
Create it free
Takes a free account
StepFun
Ale bench
694
Critpt
21 %
Proofbench
42 %
SciCode
59 %
WebDev Arena
1,570
StepFun benchmark results over time.