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

Chat & Instruction Following research benchmarks · SOTA2 Research

Chat & Instruction Following

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

Scale AI Multi-Challenge

57.3Accuracy

5

Jul 7, 2026

72.8Accuracy

4

Jul 7, 2026

90.26Win Rate

3

Apr 15, 2026

Nemotron-3-Puzzle-75B-A9B

71.9Score

1

Jul 7, 2026

Popular datasets

Arena-Hard IFBench Scale AI Multi-Challenge

Follow for updates

Join SOTA2 Contact