Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Information sensitivity and flow judgment on ConfAIde
Loading...
0.67
Tier 1 Score
Qwen2.5-7B-Instruct + CI-RL
0.5764
0.6007
0.625
0.6493
May 8, 2026
Tier 1 Score
Tier 2.a Score
Tier 2.b Score
Updated 22d ago
Evaluation Results
Method
Method
Links
Tier 1 Score
Tier 2.a Score
Tier 2.b Score
Qwen2.5-7B-Instruct + CI-RL
Training Method=CI-RL
2026.05
0.67
0.69
0.48
Qwen2.5-7B-Instruct
2026.05
0.58
0.51
0.48
Feedback
Search any
task
Search any
task