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

Embodied Instruction Following on AlfWorld (Specific Success Rates)

99.3Average Success Rate

Gemini-3-Pro

Updated 1mo ago

Evaluation Results

Method	Links
Gemini-3-Pro 2026.05		99.3	100	96.8	100	100	-	100	100
WALL-E 2.0 2026.04		98	100	100	96	100	100	94	-
DAPO+AEM 2026.05		96.6	99	100	96.3	95.2	-	93.2	91.7
DAPO 2026.05		96.1	100	100	94.7	90.3	-	94.3	96.3
ReCAPA 2026.04		96	100	97	94	95	96	94	-
RAFA 2026.04		95	100	97	91	95	100	82	-
WALL-E 1.0 2026.04		95	100	97	100	86	85	100	-
DAPO+AEM 2026.05		94.5	97.3	98.8	98.4	90.9	-	89.5	90.3
AdaPlanner 2026.04		91	100	100	89	100	97	47	-
GPT-5.2-Pro 2026.05		88.8	100	100	61.3	87	-	100	100
DAPO 2026.05		88.5	100	90.6	91.3	86.6	-	82.9	70.3
Reflexion 2026.04		86	92	94	70	81	90	88	-
GRPO+AEM 2026.05		84.4	98.9	89.4	84.1	79.5	-	65.7	78.6
GSPO+AEM 2026.05		83.4	88.9	92.6	85.2	84.8	-	78.3	56.8
EMMA 2026.04		82	71	94	85	83	88	67	-
GSPO 2026.05		80.7	95.1	73.9	80	79.8	-	69.7	66.9
PPO 2026.05		80.4	92.3	92.5	89.5	80.3	-	68.8	64
GRPO 2026.05		78.7	91.3	79.9	76.9	75.2	-	44.3	91.5
AutoGen 2026.04		77	92	74	78	86	83	41	-
GRPO+AEM 2026.05		76.8	88.6	76.4	60.9	76.7	-	69.9	67.6
DEPS 2026.04		76	93	50	80	100	100	0	-
ReAct 2026.04		74	79	54	96	85	83	51	-
GSPO+AEM 2026.05		71.9	75.5	78.1	75	70.2	-	46.7	56.5
GRPO 2026.05		68	78.2	70.5	72	75	-	39.2	49.9
GSPO 2026.05		66.7	75.4	64.6	70	74.6	-	30	54.2
PPO 2026.05		54.4	64.8	57.1	60.6	46.4	-	47.4	40.5
ReAct 2026.05		31.2	48.5	34.3	13.2	18.2	-	17.6	35.4
BUTLER 2026.04		26	31	41	60	27	12	29	-
InstructBLIP 2026.04		22	50	26	23	6	17	0	-
MiniGPT-4 2026.04		16	4	0	19	17	67	6	-
LLaMA-Adapter 2026.04		13	17	10	27	22	0	0	-
ReAct 2026.05		12.8	17.4	15.7	6.2	7.7	-	2	20.5
BLIP-2 2026.04		4	0	6	4	11	6	0	-