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

Agentic Task Performance on τ-Telehealth

45Pass^1 Rate

FAMA

22.109628.052333.99539.9377Apr 28, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.04
4537353535
2026.04
4443424140
2026.04
4337343230
2026.04
4339383534
2026.04
4241404040
2026.04
4239373535
2026.04
4240404040
2026.04
4136323130
2026.04
39.9927.9924.52220
2026.04
3938373635
2026.04
3427242220
2026.04
3224201817
2026.04
3128.5272625
2026.04
3024.5201815
2026.04
22.991612.51110
2026.04
22.9914.5111010