Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Language & Reasoning on WinoGrande (EM)
Loading...
81.5
EM Score
DeepSeek-V4-Pro Base
78.796
79.498
80.2
80.902
Apr 26, 2026
EM Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
EM Score
DeepSeek-V4-Pro Base
# Shots=0-shot, Archit...
2026.04
81.5
DeepSeek-V4-Flash Base
# Shots=0-shot, Archit...
2026.04
79.5
DeepSeek-V3.2 Base
# Shots=0-shot, Archit...
2026.04
78.9
Feedback
Search any
task
Search any
task
