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

Reward Modeling on WQ Arena

65.29Accuracy

gemini-2.5-pro

51.270854.910458.5562.1896Jan 12, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
65.29
2026.01
64.32
2026.01
63.48
2026.01
63.04
2026.01
63
2026.01
61.61
2026.01
61.15
2026.01
60.62
2026.01
59.88
2026.01
59.78
2026.01
59.61
2026.01
58.75
2026.01
58.55
2026.01
58.48
2026.01
58.14
2026.01
57.99
2026.01
57.43
2026.01
56.5
2026.01
54.21
2026.01
54.16
2026.01
53.65
2026.01
51.81