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

LLM Agent Performance research benchmarks · SOTA2 Research

LLM Agent Performance

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

AgentBoard BabyAI Naive Stream

67.5Success Rate (1)

4

Jun 2, 2026

AgentBoard BabyAI Compositional Stream

55.4Success Rate (1)

4

Jun 2, 2026

Popular datasets

AgentBoard BabyAI

Follow for updates

Join SOTA2 Contact