MEP-Bench

What is MEP-Bench?

MEP-Bench evaluates whether multimodal emotion models use modality-specific evidence sufficiently and faithfully.

Released

2026-06-24

Evaluates

General AI, Multimodal, Reasoning

Openness

unknown

Importer

Claire Radar

Review status

ai-reviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2606.25325

MEP-Bench paper and code

• Paper https://arxiv.org/abs/2606.25325
• Code https://github.com/ZhiyuanHan-Aaron/OPPO
• Website https://zjycutieee.github.io/OPPO-page/

Which sources cite MEP-Bench?

• MEP-Bench

Related General AI, Multimodal, Reasoning benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 3DCodeBench
• 5-Dialects-BN
• A-Bench
• A-OKVQA
• A3S-Bench
• AARRI-Bench
• ActBench