xbench is a new evaluation suite that scores AI agents on real-world Recruitment and Marketing tasks and uses Item Response Theory to track their capability growth over time.
If the number of returned results exceeds the actual demand, we will truncate to the specified number of objects at the beginning for evaluation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
xbench: Tracking Agents Productivity Scaling with Profession-Aligned Real-World Evaluations
xbench is a new evaluation suite that scores AI agents on real-world Recruitment and Marketing tasks and uses Item Response Theory to track their capability growth over time.