Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Truthfulness on TruthfulQA DE (norm. prob. mass and Compression)
Loading...
36.2
Normalized Probability Mass
T-Free
34.536
34.968
35.4
35.832
Mar 16, 2026
Normalized Probability Mass
Compression
Updated 1mo ago
Evaluation Results
Method
Method
Links
Normalized Probability Mass
Compression
T-Free
shots=6-shot
2026.03
36.2
5.91
HATified
shots=6-shot
2026.03
35.6
5.91
Llama
shots=6-shot
2026.03
34.7
3.39
Tülu
shots=6-shot
2026.03
34.6
3.39
Feedback
Search any
task
Search any
task
