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

Embodied AI Task Planning on EB-ALFRED

70.8Average Score

ELITE

Updated 9d ago

Evaluation Results

Method	Links
ELITE 2026.03		70.8	78	78	68	68	62	-
Claude-3.7-Sonnet 2026.04		67.7	68	70	68	68	62	70
RoboAgent 2026.04		67	72	64	78	48	60	80
Claude-3.5-Sonnet 2026.03		66.4	72	76	60	66	58	-
ERA (3B) 2026.03		65.2	72	72	62	54	66	-
Gemini-1.5-Pro 2026.03		63.2	70	72	58	64	52	-
WAP 2026.04		62.7	66	70	56	62	52	70
Gemini-1.5-Pro 2026.04		62.3	70	72	58	64	52	58
GPT-4o 2026.03		56.8	64	68	46	54	52	-
GPT-4o 2026.04		56.3	64	68	46	54	52	54
RoboGPT-R1 2026.04		55.3	62	64	50	56	50	50
VAGEN (3B) 2026.03		52.8	70	70	58	38	28	-
Gemini-2.0-flash 2026.03		51.2	62	54	46	48	46	-
RL4VLM (3B) 2026.03		51.2	70	70	56	32	28	-
Vlaser 2026.04		50	-	-	-	-	-	-
Qwen2.5-VL-72B-Ins 2026.03		49.8	55	55	50	42	47	-
Qwen-VL-Max 2026.03		43.2	44	44	42	48	38	-
Reinforced Reasoner (7B) 2026.03		41.6	54	46	28	42	38	-
Qwen-VL-Max 2026.04		41.3	44	44	42	48	38	32
Qwen2.5-VL-72B 2026.04		39.7	50	42	36	42	34	34
InternVL3-78B 2026.03		39.6	38	46	42	34	38	-
gemma-3-27b-it 2026.03		39.2	42	48	30	40	36	-
InternVL2 5-78B 2026.03		36.8	38	42	34	34	36	-
REBP 2026.04		35.6	54	46	28	42	38	6
Llama-3.2-90B-Vision 2026.03		35.2	38	44	28	34	32	-
Qwen2-VL-72B-Ins 2026.03		34.4	40	40	30	30	32	-
Ovis2-34B 2026.03		29.6	34	38	28	30	18	-
RoboBrain2.0 2026.04		14	-	-	-	-	-	-