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

Action Success Rates on ALFWorld (Interactive Agent Task)

98.9Pick Success Rate

RSPO+GiGPO

Updated 18d ago

Evaluation Results

Method	Links
RSPO+GiGPO 2026.07		98.9	88.4	100	100	85.1	91.3	95.3
GiGPO 2026.07		98.2	70.2	96.3	86.5	84.1	79.2	88.8
STAPO 2026.07		97.8	100	98.8	89.9	92.7	100	96.9
STAPO 2026.07		97.7	77.8	93.4	90.2	85.6	95.1	92.2
GiGPO 2026.07		97.7	82.7	98.8	83.7	89.3	79.2	90.8
GiGPO 2026.07		94.7	82.3	100	91.6	83.7	92.4	92.4
RSPO+PPO 2026.07		94.5	70.2	94.7	76.3	77.2	66.9	83.1
GiGPO 2026.07		94.4	67.5	94.8	94.4	79.8	76.4	86.7
RSPO+GiGPO 2026.07		92.9	85.4	97.4	94.9	89.8	73.6	90.4
EMPG 2026.07		92.9	75.2	74.8	86.3	73.7	65.3	78.5
Gemini-2.5-Pro 2026.07		92.8	63.3	62.1	69	26.6	58.7	60.3
GRPO 2026.07		92.3	73.2	92.2	67.8	71.7	54	78.4
PPO 2026.07		92.3	64	92.5	89.5	80.3	68.8	80.4
SPEAR+GRPO 2026.07		91.9	58.6	79.6	59.7	54.4	40	68.5
RSPO+GRPO 2026.07		91.4	68.2	94.4	74.6	70	60.1	80.2
GRPO 2026.07		90.8	66.1	89.3	74.7	72.5	64.7	77.6
PPO 2026.07		89.3	82.3	90	83.1	70.3	61.8	80.7
SPEAR+GiGPO 2026.07		88.4	76.3	88.7	69.6	62	78.1	78.4
RLOO 2026.07		88.3	52.8	71	62.8	66.4	56.9	69.7
RLOO 2026.07		87.6	78.2	87.3	81.3	71.9	48.9	75.5
SPEAR+GiGPO 2026.07		86.1	61.6	83.7	57.8	66.8	53.5	71.9
EMPG 2026.07		85.5	33.5	78.9	76.2	74.7	69.1	73.7
GRPO 2026.07		85.3	53.7	84.5	78.2	59.7	53.5	72.8
RSPO+PPO 2026.07		83	56.1	88.8	74.6	80	58.9	76.6
GRPO 2026.07		81.3	58.1	85.8	59.5	68.1	41	69
RSPO+GRPO 2026.07		81	64.6	81.5	73.1	74.7	65.9	74.7
PPO 2026.07		78.5	67.7	77.7	66.1	70.7	38	68
GPT-4o 2026.07		75.3	60.8	31.2	56.7	21.6	49.8	48
PPO 2026.07		64.8	40.5	57.1	60.6	46.4	47.4	54.4
SPEAR+GRPO 2026.07		62.5	50.5	64.6	35.9	37.9	34.6	50
Reflexion 2026.07		62	41.6	44.9	30.9	36.3	23.8	42.7
ReAct 2026.07		48.5	35.4	34.3	13.2	18.2	17.6	31.2
Reflexion 2026.07		35.3	22.2	21.7	13.6	19.4	3.7	21.8
Qwen2.5 2026.07		33.4	21.6	19.3	6.9	2.8	3.2	14.8
ReAct 2026.07		17.4	20.5	15.7	6.2	7.7	2	12.8
Qwen2.5 2026.07		5.9	5.5	3.3	9.7	4.2	0	4.1