Reasoning Quality Assessment on Three runs 1-5 scale (blind evaluation) benchmark leaderboard · SOTA2 Research

Reasoning Quality Assessment on Three runs 1-5 scale (blind evaluation)

4.6Recursion DepthCoT

Evaluation Results

Method	Links
CoT2026.03		4.6	3.1	4.4	4.2	5	4.7	4.33
EMoT2026.03		4	2.9	4.8	4	5	4.6	4.2