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

Long-context evaluation on 128K context

80.12Quality Score (Q)

Dense

75.606476.778277.9579.1218May 13, 2026
Updated 14d ago

Evaluation Results

MethodLinks
2026.05
80.12-59.9-2,442.2-0.313
2026.05
79.5854102.41.711,611.7340.206
2026.05
78.02-55.7-2,775.6-0.355
2026.05
77.46294.81.71,607.742.10.206
2026.05
76.56-62.9-2,360.6-0.302
2026.05
75.78781081.721,547.134.50.198