Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

MELD

Benchmarks

Task NameDataset NameSOTA ResultTrend
Emotion Recognition in ConversationMELD
Weighted Avg F170.44
180
Emotion Recognition in ConversationMELD (test)
Weighted F170.44
143
Emotion RecognitionMELD (test)
Weighted F170.12
89
Multimodal Emotion Recognition in ConversationMELD standard (test)
WF167.6
53
Multimodal Emotion Recognition in ConversationMELD
Weighted Avg F1 Score69
36
Emotion DetectionMELD (test)
Weighted-F10.699
32
Speech Emotion RecognitionMELD
Accuracy63.5
24
Emotion Recognition in ConversationMELD Standard (test)
Weighted F169.15
19
Emotion Recognition in ConversationMELD 1.0 (test)
Weighted F165.61
17
Emotion Recognition in ConversationMELD
F1 Score67.29
16
Cross-scenario Multimodal Emotion Recognition in ConversationsMELD -> IEMOCAP noise rate 40% (test)
Joy Accuracy41.46
15
Sentiment ClassificationMELD (test)
Accuracy68.5
15
Emotion Recognition in ConversationMELD
Weighted F167.12
14
Speech Emotion RecognitionMELD In-Domain v1 (test)
Accuracy54.06
14
Multimodal Empathetic Response GenerationMELD
Distinct-1 (Dist-1)28.14
12
Emotion RecognitionMELD
UACC64.34
12
Conversational Emotion RecognitionMELD (test)
Macro F1 Score61.9
12
LLM-generated text detectionMELD Overall (eval)
TPR @ 1% FPR99.9
10
LLM-generated text detectionMELD Qwen-3.6-Plus (eval)
TPR @ 1% FPR99.9
10
LLM-generated text detectionMELD-eval Claude-Haiku-4.5
TPR @ 1% FPR100
10
LLM-generated text detectionMELD GPT-5.4-Mini (eval)
TPR @ 1% FPR100
10
AI-text detectionMELD (eval)
AUROC99.99
10
Multimodal Emotion RecognitionMELD Natural Distribution
Accuracy57.43
9
Multimodal Emotion RecognitionMELD IID Setting
Accuracy55.82
9
Emotion RecognitionMELD (held-out)
F1 Score71.1
8
Showing 25 of 43 rows