Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
World Knowledge on MMLU-Redux (EM)
Loading...
90.8
Exact Match (EM)
DeepSeek-V4-Pro Base
87.368
88.259
89.15
90.041
Apr 26, 2026
Exact Match (EM)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Exact Match (EM)
DeepSeek-V4-Pro Base
# Shots=5-shot, Archit...
2026.04
90.8
DeepSeek-V4-Flash Base
# Shots=5-shot, Archit...
2026.04
89.4
DeepSeek-V3.2 Base
# Shots=5-shot, Archit...
2026.04
87.5
Feedback
Search any
task
Search any
task
