Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
World Knowledge on Simple-QA verified
Loading...
55.2
Exact Match (EM)
DeepSeek-V4-Pro Base
27.224
34.487
41.75
49.013
Apr 26, 2026
Exact Match (EM)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Exact Match (EM)
DeepSeek-V4-Pro Base
# Shots=25-shot, Archi...
2026.04
55.2
DeepSeek-V4-Flash Base
# Shots=25-shot, Archi...
2026.04
30.1
DeepSeek-V3.2 Base
# Shots=25-shot, Archi...
2026.04
28.3
Feedback
Search any
task
Search any
task
