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

Overall Capability Merging on Multi-Task Average

56.56Avg Accuracy

SWUDI

48.000850.222952.44554.6671Jun 5, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
56.56
2026.06
56.33
2026.06
56.22
2026.06
56.18
2026.06
56
2026.06
55.87
2026.06
55.85
2026.06
55.35
2026.06
55.17
2026.06
53.8
2026.06
53.48
2026.06
52.5
2026.06
48.33