Commonsense Reasoning on 30 sampled commonsense reasonings (n=7 agents) benchmark leaderboard · SOTA2 Research

Commonsense Reasoning on 30 sampled commonsense reasonings (n=7 agents)

0.695IAACP-WBFT

Evaluation Results

Method	Links
CP-WBFT2026.05		0.695	0.371	0.324	0.267	0.77	0.52	0.83	0.39	0.267
SAC2026.05		0.695	0.695	0	0.833	0.77	0.8	0.83	0.82	0.833
CP-WBFT2026.05		0.69	0.143	0.547	0.167	0.72	0.17	0.85	0.17	0.167
CP-WBFT2026.05		0.69	0.205	0.485	0.233	0.75	0.25	0.83	0.23	0.233
SAC2026.05		0.69	0.662	0.028	0.733	0.73	0.75	0.84	0.78	0.767
SAC2026.05		0.686	0.667	0.019	0.767	0.73	0.77	0.83	0.78	0.8