Emotion Interpretation on EIBench

Metric: Recall (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Recall▼	Extra Data	Paper	Date↕	Code
1	Claude-3-haiku	63.24	No	Why We Feel: Breaking Boundaries in Emotional Re...	2025-04-10	Code
2	LLaVA-1.5 (13B)	54.37	No	Why We Feel: Breaking Boundaries in Emotional Re...	2025-04-10	Code
3	LLaVA-NEXT (13B)	54.33	No	Why We Feel: Breaking Boundaries in Emotional Re...	2025-04-10	Code
4	Claude-3-sonnet	54.1	No	Why We Feel: Breaking Boundaries in Emotional Re...	2025-04-10	Code
5	LLaVA-NEXT (7B)	53.82	No	Why We Feel: Breaking Boundaries in Emotional Re...	2025-04-10	Code
6	MiniGPT-v2	52.89	No	Why We Feel: Breaking Boundaries in Emotional Re...	2025-04-10	Code
7	ChatGPT-4o	49.99	No	Why We Feel: Breaking Boundaries in Emotional Re...	2025-04-10	Code
8	Video-LLaVA	49.26	No	Why We Feel: Breaking Boundaries in Emotional Re...	2025-04-10	Code
9	LLaVA-NEXT (34B)	49.03	No	Why We Feel: Breaking Boundaries in Emotional Re...	2025-04-10	Code
10	ChatGPT-4V	46.86	No	Why We Feel: Breaking Boundaries in Emotional Re...	2025-04-10	Code
11	Otter	42.81	No	Why We Feel: Breaking Boundaries in Emotional Re...	2025-04-10	Code
12	Qwen-vl-plus	31	No	Why We Feel: Breaking Boundaries in Emotional Re...	2025-04-10	Code
13	Qwen-VL-Chat	26.45	No	Why We Feel: Breaking Boundaries in Emotional Re...	2025-04-10	Code

#1Claude-3-haikuSOTA
63.24
Recall· 2025-04-10
Why We Feel: Breaking Boundaries in Emotional Reasoning with Multimodal Large Language Models Code
#2LLaVA-1.5 (13B)
54.37
Recall· 2025-04-10
Why We Feel: Breaking Boundaries in Emotional Reasoning with Multimodal Large Language Models Code
#3LLaVA-NEXT (13B)
54.33
Recall· 2025-04-10
Why We Feel: Breaking Boundaries in Emotional Reasoning with Multimodal Large Language Models Code
#4Claude-3-sonnet
54.1
Recall· 2025-04-10
Why We Feel: Breaking Boundaries in Emotional Reasoning with Multimodal Large Language Models Code
#5LLaVA-NEXT (7B)
53.82
Recall· 2025-04-10
Why We Feel: Breaking Boundaries in Emotional Reasoning with Multimodal Large Language Models Code
#6MiniGPT-v2
52.89
Recall· 2025-04-10
Why We Feel: Breaking Boundaries in Emotional Reasoning with Multimodal Large Language Models Code
#7ChatGPT-4o
49.99
Recall· 2025-04-10
Why We Feel: Breaking Boundaries in Emotional Reasoning with Multimodal Large Language Models Code
#8Video-LLaVA
49.26
Recall· 2025-04-10
Why We Feel: Breaking Boundaries in Emotional Reasoning with Multimodal Large Language Models Code
#9LLaVA-NEXT (34B)
49.03
Recall· 2025-04-10
Why We Feel: Breaking Boundaries in Emotional Reasoning with Multimodal Large Language Models Code
#10ChatGPT-4V
46.86
Recall· 2025-04-10
Why We Feel: Breaking Boundaries in Emotional Reasoning with Multimodal Large Language Models Code
#11Otter
42.81
Recall· 2025-04-10
Why We Feel: Breaking Boundaries in Emotional Reasoning with Multimodal Large Language Models Code
#12Qwen-vl-plus
31
Recall· 2025-04-10
Why We Feel: Breaking Boundaries in Emotional Reasoning with Multimodal Large Language Models Code
#13Qwen-VL-Chat
26.45
Recall· 2025-04-10
Why We Feel: Breaking Boundaries in Emotional Reasoning with Multimodal Large Language Models Code