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

AlpacaEval dataset and benchmarks – Page 5 · SOTA2 Research

Research Datasets

AlpacaEval

Benchmarks

Task NameDataset NameSOTA MethodSort

Task NameDataset NameSOTA ResultTrendResults

Speech-to-speech Instruction Following

AlpacaEval

2.8GPTScore

3

Speech-to-text Instruction Following

AlpacaEval

3.9GPTScore

3

Dialogue turn-taking

AlpacaEval

100Success Rate

3

Prompt Inversion

AlpacaEval

18.57A1 Score

2

Audio-language generation

AlpacaEval VoiceBench

3.78Score

2

Page 5 of 5

Popular tasks

Instruction Following LLM Alignment Chat Preference Alignment LLM Evaluation

Follow for updates

Join SOTA2 Contact