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-R1, gpt-6-astra_max, gemini-3.8-flash_high and 7 more, by GPQA Diamond.
Create it free
Takes a free account
DeepSeek-R1
Aider Polyglot
0.57 %
Algotune
0.02 %
Arc Agi
0.16 %
Arc Agi 2
0.01 %
BALROG
0.35 %
Critpt
0.01 %
Forecastbench
0.60 %
GPQA Diamond
0.69 %
Lech Mazur Writing
0.08 %
Live bench
0.72 %
Math Level 5
0.93 %
OTIS Mock AIME 2024 2025
0.53 %
SciCode
0.36 %
SimpleBench
0.31 %
WeirdML
0.36 %
Training Compute
3,500,000,000,000.00T FLOP
DeepSeek-R1 benchmark results.