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

Long-context understanding on LongBench (Specific Metric Subset)

27.7Qasper Score

LongChat-7B-v1.5

13.940817.512921.08524.6571Jun 7, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
27.722.782.34368.526.115.440.81
2026.06
25.1923.29239.972.526.915.9142.23
2026.06
23.8122.6480.6144.1564.525.414.0839.31
2026.06
23.222.489.0636.346725.8913.239.58
2026.06
22.5822.481.341.046525.715.639.09
2026.06
21.122.475.8140.7862.522.612.5836.8
2026.06
15.3822.173.3627.5863.521.661.9532.21
2026.06
14.4723.386.7126.577326.198.3336.93