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

Open-ended Generation on Arena-Hard

84.6Score

AR-MAP

39.339251.089662.8474.5904Feb 2, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
84.6
2026.02
81.8
2026.02
73.55
2026.02
72.2
2026.02
71.23
2026.02
68.14
2026.02
67.8
2026.02
61.12
2026.02
61.08
2026.02
60.4
2026.02
57.4
2026.02
55.04
2026.02
50.2
2026.02
41.08