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

Generation research benchmarks – Page 3 · SOTA2 Research

Generation

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

Synthetic image dataset

Rare-Aware Autoencoding

221.8FID

2

Apr 3, 2026

AILS-NTUA system

0.77HM Score

2

Mar 12, 2026

WizardLM (test)

48.37LLM-as-a-Judge Score

2

Feb 26, 2026

SelfInst (test)

60.16LLM-as-a-Judge Score

2

Feb 26, 2026

VicunaEval (test)

56.07LLM Judge Score

2

Feb 26, 2026

DollyEval (test)

62.02LLM-as-a-Judge Score

2

Feb 26, 2026

Page 3 of 3

Popular datasets

Torus DVisRAG SQuAD Spider ViDoRe

Follow for updates

Join SOTA2 Contact