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

Long-context evaluation on L-Eval

68.8Close Score

InternLM2-Chat-20B-SFT

11.39226.29641.256.104Mar 26, 2024
Updated 1mo ago

Evaluation Results

MethodLinks
2024.03
68.84249.4
2024.03
68.740.848.6
2024.03
68.640.848.5
2024.03
68.640.648.4
2024.03
65.335.643.9
2024.03
59.13541.7
2024.03
54.33439.7
2024.03
40.632.334.6
2024.03
36.132.433.4
2024.03
35.333.534
2024.03
27.334.432.5
2024.03
2033.129.4
2024.03
13.632.627.3