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

Open-ended generation research benchmarks – Page 3 · SOTA2 Research

Open-ended generation

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

0.512Exact Match (EM)

4

Feb 26, 2026

RealToxicityPrompts Non-toxic prompts (test)

7.38Toxicity Probability

4

Feb 26, 2026

7.06Generation Score

3

Jun 19, 2026

MT-Bench (test)

82.5Win Rate

2

Feb 26, 2026

RealToxicityPrompts Toxic prompts (test)

74.29Toxicity Probability

2

Feb 26, 2026

WVS-based Open-ended Generation Dataset 65 questions (test)

0.215Score (Ar)

1

Feb 26, 2026

Page 3 of 3

Popular datasets

TruthfulQA LLaVA-Bench NQ AlpacaEval MATH

Follow for updates

Join SOTA2 Contact