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

Instruction Following and Agent Capabilities research benchmarks · SOTA2 Research

Instruction Following and Agent Capabilities

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

Agent & Alignment Suite

Qwen3-30B-A3B-Instruct-2507

84.29IFEval Strict Prompt Score

4

Feb 26, 2026

Popular datasets

Agent & Alignment Suite

Follow for updates

Join SOTA2 Contact