Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Safety on Winogender
Loading...
65.3
Normalized Log Accuracy
T-Free
53.236
56.368
59.5
62.632
Mar 16, 2026
Normalized Log Accuracy
Compression Ratio
Updated 1mo ago
Evaluation Results
Method
Method
Links
Normalized Log Accuracy
Compression Ratio
T-Free
shots=5-shot
2026.03
65.3
5.23
Llama
shots=5-shot
2026.03
64.2
4.8
Llama
shots=5-shot
2026.03
62.8
4.8
HATified
shots=5-shot
2026.03
62.1
5.23
T-Free
shots=5-shot
2026.03
59
5.23
HATified
shots=5-shot
2026.03
56.7
5.23
Tülu
shots=5-shot
2026.03
55.4
4.8
HATified
shot_count=5-shot
2026.03
55
5.23
Tülu
shot_count=5-shot
2026.03
53.7
4.8
Feedback
Search any
task
Search any
task
