Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Correctness Prediction on GSM8K (test)
Loading...
0.852
Best-layer ROC-AUC
Trajectory features
0.64088
0.69569
0.7505
0.80531
Apr 7, 2026
Best-layer ROC-AUC
Updated 11d ago
Evaluation Results
Method
Method
Links
Best-layer ROC-AUC
Trajectory features
2026.04
0.852
LogitLens
config=best config
2026.04
0.765
Step-count only
2026.04
0.649
Feedback
Search any
task
Search any
task
