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

Long-context Reasoning on FRAMES

84.7Score

Claude-Opus-4.5

69.72473.61277.581.388May 29, 2026Jun 3, 2026Jun 8, 2026Jun 14, 2026Jun 19, 2026Jun 24, 2026Jun 30, 2026
Updated 23d ago

Evaluation Results

MethodLinks
84.7
84.5
84
2026.06
83.7
2026.05
83.5
83.4
2026.06
82.9
2026.05
81.9
2026.05
81.9
81.9
2026.05
81.7
2026.05
80.7
80.5
2026.05
79.6
2026.05
79.5
78.7
2026.05
78.5
2026.05
78.3
2026.05
76.7
2026.05
76.1
2026.05
75.8
2026.05
74.3
2026.05
73.4
2026.05
73.2
2026.05
73.1
2026.05
72.6
2026.05
70.3