Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Multi-Agent Strategic Reasoning on ConnectFour OOD

99.93First-mover Normalized Score

GPT-5-mini

48.522861.868975.21588.5611May 6, 2026
Updated 27d ago

Evaluation Results

MethodLinks
2026.05
99.9397.95
2026.05
96.9772.1
2026.05
78.7482.7
2026.05
75.9369.26
2026.05
70.6767
2026.05
70.3970.26
2026.05
68.7159.24
2026.05
6860.85
2026.05
66.9869.94
2026.05
64.966.14
2026.05
64.162.34
2026.05
63.257.01
2026.05
62.7758.39
2026.05
61.1458.66
2026.05
58.1158.12
2026.05
5864.88
2026.05
56.6263.63
2026.05
50.557.01