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 Evaluation research benchmarks · SOTA2 Research

Chat Evaluation

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

AlpacaEval LC 2

DictaLM 3.0 24B-Think

74.11Score

23

Feb 27, 2026

2.14Speedup

16

Jun 26, 2026

24.1Throughput (TPS)

10

Mar 12, 2026

Popular datasets

MT-Bench AlpacaEval

Follow for updates

Join SOTA2 Contact