Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
World Knowledge on SuperGPQA (EM)
Loading...
53.9
EM
DeepSeek-V4-Pro Base
44.644
47.047
49.45
51.853
Apr 26, 2026
EM
Updated 1mo ago
Evaluation Results
Method
Method
Links
EM
DeepSeek-V4-Pro Base
# Shots=5-shot, Archit...
2026.04
53.9
DeepSeek-V4-Flash Base
# Shots=5-shot, Archit...
2026.04
46.5
DeepSeek-V3.2 Base
# Shots=5-shot, Archit...
2026.04
45
Feedback
Search any
task
Search any
task
