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

Multi-turn MLLM Safety Evaluation research benchmarks · SOTA2 Research

Multi-turn MLLM Safety Evaluation

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

STEER Average Multi-turn

64.89Safety Score

18

Apr 21, 2026

STEER-DyS Multi-turn

61.36Safety Score

18

Apr 21, 2026

STEER-SPA Multi-turn

66.67Safety

18

Apr 21, 2026

STEER-VLS Multi-turn

65.96Safety Score

18

Apr 21, 2026

STEER-MMSafe Multi-turn

77.04Safety Score

18

Apr 21, 2026

STEER-Beaver Multi-turn

55.58Safety

18

Apr 21, 2026

Popular datasets

STEER-Beaver STEER-MMSafe STEER-VLS STEER-SPA STEER-DyS

Follow for updates

Join SOTA2 Contact