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

Tool Use Evaluation research benchmarks · SOTA2 Research

Tool Use Evaluation

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

0.923Similarity

19

Apr 8, 2026

89.4Average Score

11

Feb 26, 2026

OpenEarthAgent Step-by-step evaluation tool-agnostic rollouts

0.995Instruction Adherence

9

Feb 26, 2026

ShortcutsBench clear instructions 200 queries

92.5API Selection Accuracy

8

Apr 30, 2026

81.8Precision

7

Mar 11, 2026

Popular datasets

GTM ToolSandbox MCPToolBench OpenEarthAgent ShortcutsBench

Follow for updates

Join SOTA2 Contact