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 Learning research benchmarks · SOTA2 Research

Tool Learning

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

86.2Success Rate

50

Jun 2, 2026

StableToolBench Average

70.3SoPR

13

Feb 26, 2026

StableToolBench I3-Inst.

76SoPR

13

Feb 26, 2026

StableToolBench I2-Cat.

71.9SoPR

13

Feb 26, 2026

StableToolBench I2-Inst.

GPT-4 (Parallel)

73.4SoPR

13

Feb 26, 2026

StableToolBench I1-Cat.

GPT-4 (Parallel)

70.9SoPR

13

Feb 26, 2026

StableToolBench I1-Tool

GPT-3.5 (DFSDT)

73.9SoPR

13

Feb 26, 2026

StableToolBench I1-Inst.

69SoPR

13

Feb 26, 2026

62.41Correctness

10

Feb 26, 2026

RestBench Spotify

87.72Success

10

Feb 26, 2026

Popular datasets

StableToolBench RestBench API-Bank

Follow for updates

Join SOTA2 Contact