List your company

ResearchFormerly WizWand

ItaBench

Benchmarks

TaskDatasetSOTA resultTrendResults

Complex Reasoning and Instruction Following

ItaBench leaderboard tasks

37.88BBH-it Score

6

Multiple Choice Question Answering

ItaBench translated multiple-choice

57.92ARC-E (Italian)

6

Machine Translation

Italian ItaBench trans-mc

0.542Average Performance

6