Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

WorkBench dataset and benchmarks · SOTA2 Research

Research Datasets

WorkBench

Benchmarks

Task NameDataset NameSOTA MethodSort

Task NameDataset NameSOTA ResultTrendResults

Misalignment Detection

WorkBench (n=326)

52Average IR

30

Misalignment Detection

Workbench n=62 (general)

0.3Error Rate (ER)

30

Multi-agent system task solving

workbench

82.4Accuracy

21

Job and Skill Intelligence Tasks

WorkBench (test)

17.9Job2Skill MAP

9

WorkBench

13.2Latency (ms)

9

WorkBench

92.59Analytics Success Rate

4

General Purpose Tool Use

WorkBench

86.11Analytics Success Rate

4

Multi-tool Coordination

Workbench

0.267Beta_Ec x T

1

Popular tasks

Misalignment Detection Ranking Agent Tool Use Job and Skill Intelligence Tasks Multi-agent system task solving

Follow for updates

Join SOTA2 Contact