List your company

Web Automation on WebArena

53.7Success RateSKILL.nb
14.1824.4434.744.96Jun 3, 2026Jun 5, 2026Jun 7, 2026Jun 9, 2026Jun 11, 2026Jun 13, 2026Jun 16, 2026

Evaluation results

MethodLinks
SKILL.nbEvaluation Protocol=single-round, Task Initialization=starts without task-specific persistent state2026.0653.75256.270.354.450.817.5———————
ReasoningBankEvaluation Protocol=single-round, Task Initialization=starts without task-specific persistent state2026.0649.852.155.868.945.242.111.3———————
PolySkill2026.0649.351.454.873.254.218.918.95.56.34.56.849.55.9
ASI2026.0646.546.353.673.746.821.515.15.86.64.87.14.3106.2
AWMonlineEvaluation Protocol=single-round, Task Initialization=starts without task-specific persistent state2026.0646.448.149.368.94045.35.7———————
SKILLMIGRATOR2026.0645.745.552.772.646.719.316.74.85.64.56.739.45.4
SkillWeaver2026.0643.639.348.271.250.317.216.35.76.54.774.29.86.1
ReAct2026.0638.537.4446638.916.410.36.1757.54.510.56.5
CodeActEvaluation Protocol=single-round, Task Initialization=starts without task-specific persistent state2026.0638.33944.555.731.233.910.2———————
SGDRModel=GPT-4.1, # Steps=4.82026.0637.534.647.735.934.232.3————————
CERModel=GPT-4.1, # Steps=6.42026.0633.93138.431.137.128.6————————
ASIModel=GPT-4.1, # Steps=5.22026.063329.641.433.829.729.4————————
VanillaModel=GPT-4.1, # Steps=6.02026.0628.32935.921.62821.1————————
AWMModel=GPT-4.1, # Steps=5.92026.0627.826.736.424.128.517.6————————
SGDRModel=QWEN3-4B, # Steps=5.62026.0624.325.124.622.826.719.6————————
CERModel=QWEN3-4B, # Steps=6.52026.0622.123.320.720.227.515.5————————
ASIModel=QWEN3-4B, # Steps=5.92026.0620.822.522.619.222.314.2————————
VanillaModel=QWEN3-4B, # Steps=6.32026.0616.521.914.812.716.613.5————————
AWMModel=QWEN3-4B, # Steps=5.72026.0615.719.812.713.318.511.4————————