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

GitLab dataset and benchmarks · SOTA2 Research

Research Datasets

GitLab

Benchmarks

Task NameDataset NameSOTA MethodSort

Task NameDataset NameSOTA ResultTrendResults

Instruction Injection Attack on Web Browser Agent

GitLab Short

100UUA

16

Instruction Injection Attack on Web Browser Agent

GitLab Medium

100UUA

16

Instruction Injection Attack on Web Browser Agent

GitLab Long

100UUA

16

Autonomous Task Completion

GitLab

66.2Success Rate (SR)

6

Web Task Completion

Gitlab

87Accuracy

5

Web Agent Automation

Gitlab

9.9End-to-end Latency (seconds)

5

Popular tasks

Instruction Injection Attack on Web Browser Agent Web Task Completion Autonomous Task Completion Web Agent Automation

Follow for updates

Join SOTA2 Contact