Benchmark

Meld

MELD (Multimodal EmotionLines Dataset) is a multimodal multi-party dataset for emotion recognition in conversations. Contains approximately 13,000…

Modality
multimodal
Categories
multimodal, psychology, creativity
Openness
unknown
Source
llm_stats
Reported scores
1

Reported scores

llm_stats

ModelOrganizationReported valueReportedEvidence
Qwen2.5-Omni-7BQwen0.572025-03-27evidence

Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.