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

Alignment research benchmarks – Page 2 · SOTA2 Research

Alignment

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

MT-Bench v1 (test)

8.41MT-Bench Score

5

Feb 26, 2026

70.4Hard Prompt Gemini Score

4

Feb 26, 2026

Qwen2-72B-Instruct

8.27Score

4

Feb 26, 2026

MixEval v1 (test)

76.5Accuracy

4

Feb 26, 2026

(n)ASAP Dataset piano performances

6Mean Error (ms)

3

May 20, 2026

Collaborative Manipulation Simulation Alignment, 2 Robots

9Success Rate

2

May 26, 2026

Top Performing System

81.5Micro F1

2

Apr 30, 2026

Page 2 of 2

Popular datasets

Berlin MT-Bench IFEval AlignBench Arena

Follow for updates

Join SOTA2 Contact