Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
World Knowledge on FACTS Parametric
Loading...
62.6
EM
DeepSeek-V4-Pro Base
25.68
35.265
44.85
54.435
Apr 26, 2026
EM
Updated 1mo ago
Evaluation Results
Method
Method
Links
EM
DeepSeek-V4-Pro Base
# Shots=25-shot, Archi...
2026.04
62.6
DeepSeek-V4-Flash Base
# Shots=25-shot, Archi...
2026.04
33.9
DeepSeek-V3.2 Base
# Shots=25-shot, Archi...
2026.04
27.1
Feedback
Search any
task
Search any
task
