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 DeepSeek-V3.1, gemini-4-argon_high, gpt-6-astra_max and 7 more, by GPQA Diamond.
Create it free
Takes a free account

DeepSeek-V3.1

Forecastbench
61 %
SimpleBench
40 %
WeirdML
38 %
Training Compute
3,594,058,000,000.00T FLOP
DeepSeek-V3.1 benchmark results.

Forecastbench Monthly

Forecastbench score.

Forecastbench Yearly

Forecastbench score.

SimpleBench Monthly

SimpleBench score.

SimpleBench Yearly

SimpleBench score.

WeirdML Monthly

WeirdML score.

WeirdML Yearly

WeirdML score.