Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Finite-answer lead measurement on Quality-gated parser-clean replication dataset v1 (test)
Loading...
100
Parse Accuracy
finite-answer commitment
95
97.5
100
102.5
May 7, 2026
Parse Accuracy
Parsed Accuracy
Sample Accuracy
Commit Score
Mean Onset
Mean Lead
Updated 23d ago
Evaluation Results
Method
Method
Links
Parse Accuracy
Parsed Accuracy
Sample Accuracy
Commit Score
Mean Onset
Mean Lead
finite-answer commitment
Condition=Canonical, S...
2026.05
100
100
100
100
42.7
3.5
finite-answer commitment
Condition=Prompt shift...
2026.05
100
100
100
100
55.99
4.74
finite-answer commitment
Condition=Task-family...
2026.05
100
100
100
100
42.56
13.72
finite-answer commitment
Condition=Verbalizer s...
2026.05
100
100
100
100
52.01
4.22
Feedback
Search any
task
Search any
task