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

Reward Modeling on HREF

75.95Accuracy

gpt-5-2025-08-07

54.026859.718465.4171.1016Jan 12, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
75.95
2026.01
73.84
2026.01
73.64
2026.01
73.47
2026.01
73.47
2026.01
73.22
2026.01
72.73
2026.01
71.65
2026.01
70.99
2026.01
70.58
2026.01
69.67
2026.01
69.34
2026.01
69.26
2026.01
67.77
2026.01
65.04
2026.01
64.96
2026.01
64.88
2026.01
62.19
2026.01
58.99
2026.01
57.77
2026.01
56.78
2026.01
54.87