Safety
FaithCoT-Bench (released FINE-CoT generator measurements)
Released reasoning trajectories from four models on four task suites, with human faithfulness annotations and parsed-answer correctness.
684items
4subjects
No dataset license is specified in the captured author repository.license
reasoningdomain
safetydomain
textmodality
item-level responses released
Saturation status: No
Response matrix
Loading response matrix…
Correct (1)Incorrect (0)Unobserved
Scale: 1 = correct · 0 = incorrect