Benchmarks

Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.

309,131 indexed

Task	Dataset	Domain	Results	Last Update
Multimodal Language Model Unlearning	MLLMU-Bench 1.0 (Retain Set)	multimodalllm chat instruction	30	Jun 2, 2026
Multimodal Language Model Unlearning	MLLMU-Bench 1.0 (test)	multimodalllm chat instruction	30	Jun 2, 2026
Multimodal Language Model Unlearning	MLLMU-Bench forget set 1.0	multimodalllm chat instruction	30	Jun 2, 2026
Open-Ended Generation	MLLMU-Bench (Retain Set)	llm chat instruction	30	Jun 2, 2026
Cloze Task	MLLMU-Bench (Retain Set)	nlp