List your company

ResearchFormerly WizWand

EXPLORE-Bench

Benchmarks

TaskDatasetSOTA resultTrendResults

Long-horizon reasoning

EXPLORE-Bench Full

65.59Sobj Score

6

Long-horizon reasoning

EXPLORE-Bench Long

59.37Sobj Score

6

Long-horizon reasoning

EXPLORE-Bench Medium

66.71Sobj Score

6

Long-horizon reasoning

EXPLORE-Bench Short

66.12Object Score

6