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

Task Completion on SOP-Bench

100Accuracy

GA

79.284.69095.4Jun 6, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
1002.02532.080.48
2026.06
1002.6402.640.38
2026.06
1008574590222.18
2026.06
1009145196520.73
2026.06
100000-
2026.06
951.2601.2615.13
2026.06
95145815319.63
2026.06
851.23231.250.68
2026.06
801.34571.3911.47