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

Averaged Performance across Five Downstream Tasks on Average Overall

2.49Speedup

No Filter

2.13642.22822.322.4118Jan 26, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
2.492.78
2026.01
2.412.56
2026.01
2.232.49
2026.01
2.212.49
2026.01
2.22.46
2026.01
2.22.49
2026.01
2.22.48
2026.01
2.152.4