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

DeepSeek-V3.1_thinking

Dtbench
83 %
Lmca
24 %
WeirdML
38 %
Training Compute
3,594,058,000,000.00T FLOP
DeepSeek-V3.1_thinking benchmark results.

Dtbench Monthly

Dtbench score.

Dtbench Yearly

Dtbench score.

Lmca Monthly

Lmca score.

Lmca Yearly

Lmca score.

WeirdML Monthly

WeirdML score.

WeirdML Yearly

WeirdML score.