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

Long-context Understanding on RULER 64K context 1.0 (test)

100N-S Score 1

Dense

-4235077Mar 10, 2025
Updated 16d ago

Evaluation Results

MethodLinks
2025.03
10010010010010095.8384.3860.4290.6386.8191.81
2025.03
10097.9296.8898.9697.491.1564.5856.2573.7561.4683.84
2025.03
10010010098.9610090.6380.2158.3382.0881.9489.22
2025.03
10096.8897.9231.2595.3183.0784.3859.3891.2580.5682
2025.03
10093.7596.8816.6790.3780.7384.3859.3889.1776.3978.77
2025.03
10010010096.8899.4790.6384.3858.3389.1782.6490.15
2025.03
26.040000012.514.580.423.475.7
2025.03
15.6312.512.59.3814.8417.7146.8843.7513.1389.2427.56
2025.03
02.083.1313.5400.7848.9643.7536.4640.6318.93