Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Open-ended Dialogue on TruthfulQA OOD
Loading...
52.2
Wins
CausalRM
30.88
36.415
41.95
47.485
Jan 29, 2026
Wins
Ties
Losses
Updated 1mo ago
Evaluation Results
Method
Method
Links
Wins
Ties
Losses
CausalRM
Opponent=SFT
2026.01
52.2
41.2
6.6
CausalRM
Opponent=Standard RM
2026.01
50.9
30.4
18.7
CausalRM
Opponent=InfoRM
2026.01
44.1
39.7
16.2
CausalRM
Opponent=GoalRM
2026.01
31.7
52.9
15.4
Feedback
Search any
task
Search any
task
