Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Truthfulness on TruthfulQA (norm. prob. mass and compression)
Loading...
36.4
Normalized Probability Mass
T-Free
34.944
35.322
35.7
36.078
Mar 16, 2026
Normalized Probability Mass
Compression Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Normalized Probability Mass
Compression Score
T-Free
shots=6-shot
2026.03
36.4
4.91
HATified
shots=6-shot
2026.03
35.7
4.91
Llama
shots=6-shot
2026.03
35
4.18
Tülu
shots=6-shot
2026.03
35
4.18
Feedback
Search any
task
Search any
task