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

Social Intelligence Reasoning on IntentBench

68.6Why Score

Gemini-2.5-Pro (think)

52.58456.74260.965.058Jun 10, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
68.667.457.1647067.2
2026.06
68.265.857.17668.366.7
2026.06
67.269.564.38475.570.3
2026.06
66.867.1508472.469.3
2026.06
62.663.457.1766964.2
2026.06
61.555.735.77663.360
2026.06
60.655.464.37662.957.4
2026.06
57.953.557.16861.154.5
2026.06
53.249.471.46461.154.2