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

Web Shopping Agent on WebShop (Score, SR, Steps)

82.9Success Rate (SR)

Skill1

Updated 16d ago

Evaluation Results

Method
Skill1 2026.05	82.9	89.7	-	-	-	-	-	-
SDAR 2026.05	82.8	89.4	-	-	-	-	-	-
RetroAgent 2026.05	82.3	88.9	-	-	-	-	-	-
D2Skill 2026.05	80.5	91.1	-	-	-	-	-	-
RLSD 2026.05	77.3	87.4	-	-	-	-	-	-
GRPO+OPSD 2026.05	76.5	86.8	-	-	-	-	-	-
Skill-SD 2026.05	76.5	86.1	-	-	-	-	-	-
SKILLC 2026.05	74	85.6	-	-	-	-	-	-
GiGPO 2026.05	72.8	84.4	-	-	-	-	-	-
SKILLRL 2026.05	72.7	85.2	-	-	-	-	-	-
SKILL0 2026.05	70.9	83.3	-	-	-	-	-	-
AgentLM-13B 2026.07	70.8	-	-	-	-	-	-	-
PPO 2026.05	68.7	81.4	-	-	-	-	-	-
GRPO 2026.05	66.1	79.3	-	-	-	-	-	-
RLOO 2026.05	65.7	80.3	-	-	-	-	-	-
AgentLM-70B 2026.07	64.9	-	-	-	-	-	-	-
Hephaestus-8B-IFT 2026.07	63.9	-	-	-	-	-	-	-
AgentLM-7B 2026.07	63.6	-	-	-	-	-	-	-
Hephaestus-8B-Base 2026.07	60.5	-	-	-	-	-	-	-
EPPO 2026.07	57.5	-	-	-	-	-	-	-
AgentRL 2026.07	51.3	-	-	-	-	-	-	-
DCPO 2026.07	50.5	-	-	-	-	-	-	-
BAPO 2026.07	48.2	-	-	-	-	-	-	-
Reflexion 2026.06	45	69	-	-	-	-	-	-
UCE 2026.06	42	61.3	-	-	-	-	-	-
Plan-and-Act + ECU 2026.06	42	62.7	-	-	-	-	-	-
SKillOS 2026.05	41.3	56	18.3	-	-	-	-	-
SKillOS-gemini 2026.05	41	54.7	17.8	-	-	-	-	-
NoThinking + ECU 2026.06	41	66.8	-	-	-	-	-	-
ReasoningBank 2026.05	40.2	50.8	19.2	-	-	-	-	-
NoThinking + ECU 2026.06	40	65.6	-	-	-	-	-	-
MemP 2026.05	39.8	51.3	19.4	-	-	-	-	-
SKillOS-base 2026.05	39.6	52.8	19	-	-	-	-	-
ReflAct + ECU 2026.06	39	61.5	-	-	-	-	-	-
No Memory 2026.05	38.4	48.6	19.5	-	-	-	-	-
Claude-Sonnet-4 Thinking 2026.07	38.3	-	-	-	-	-	-	-
NoThinking 2026.06	37	58.7	-	-	-	-	-	-
Plan-and-Act + ECU 2026.06	37	56.8	-	-	-	-	-	-
Claude-Sonnet-4 2026.07	34.6	-	-	-	-	-	-	-
ReflAct + ECU 2026.06	34	57.4	-	-	-	-	-	-
GPT-5 2026.07	33.7	-	-	-	-	-	-	-
o3-mini 2026.07	32.7	-	-	-	-	-	-	-
Plan-and-Act 2026.06	31	52	-	-	-	-	-	-
DeepSeek-R1 2026.07	31	-	-	-	-	-	-	-
ReAct 2026.06	30	45.1	-	-	-	-	-	-
UCE 2026.06	29	51	-	-	-	-	-	-
Reflexion 2026.05	28.8	58.1	-	-	-	-	-	-
o4-mini 2026.07	28.5	-	-	-	-	-	-	-
Qwen2.5-32B-Instruct 2026.07	27.5	-	-	-	-	-	-	-
ReflAct 2026.06	24	39.6	-	-	-	-	-	-
DeepSeek-V3 2026.07	23.4	-	-	-	-	-	-	-
ReAct 2026.05	19.5	46.2	-	-	-	-	-	-
ExpeL 2026.06	18	31.6	-	-	-	-	-	-
EvolveR 2026.05	17.6	42.5	-	-	-	-	-	-
Qwen2.5-14B-Instruct 2026.07	17.6	-	-	-	-	-	-	-
SKillOS 2026.05	16.5	40.6	19.4	-	-	-	-	-
SKillOS 2026.05	16.5	49.2	15.9	-	-	-	-	-
SKillOS-base 2026.05	13.6	38.6	20.1	-	-	-	-	-
SKillOS-gemini 2026.05	13.2	38.1	19.6	-	-	-	-	-
SKillOS-gemini 2026.05	13.2	45.2	16.6	-	-	-	-	-
SKillOS-base 2026.05	12.3	43.4	16.8	-	-	-	-	-
No Memory 2026.05	12.2	41.5	17	-	-	-	-	-
MemP 2026.05	12	35.7	21.3	-	-	-	-	-
ReasoningBank 2026.05	11.4	35.4	20.5	-	-	-	-	-
ReasoningBank 2026.05	11.2	40.4	17.9	-	-	-	-	-
ExpeL 2026.05	11.2	30.9	-	-	-	-	-	-
MemP 2026.05	10.1	30.7	17.4	-	-	-	-	-
No Memory 2026.05	9.8	33.3	20.3	-	-	-	-	-
Zero-Shot 2026.05	7.8	26.4	-	-	-	-	-	-
Qwen2.5-3B-Instruct 2026.07	5.3	-	-	-	-	-	-	-
OPSD 2026.05	2.3	4.5	-	-	-	-	-	-
Mem0 2026.05	2	23.9	-	-	-	-	-	-
Zero-shot 2026.05	-	-	-	4.4	4.6	3.4	1	3.5
Few-shot 2026.05	-	-	-	14.2	15.1	13.5	24	16.5
ReAct 2026.05	-	-	-	12.4	11.1	4.5	12	10.4
Reflexion 2026.05	-	-	-	3.5	8.6	1.1	7	5.5
Mem0 2026.05	-	-	-	8.9	9.2	2.3	11	8.2
ExpeL 2026.05	-	-	-	6.2	12.5	9	21	12.1
MemP 2026.05	-	-	-	15.9	13.2	9	19	14.3
SimpleMem 2026.05	-	-	-	11.5	13.8	6.7	13	11.7
RLOO 2026.05	-	-	-	34.9	23.9	41.5	32.1	31.1
GRPO 2026.05	-	-	-	35.1	22.6	39	49.5	33.6
MemRL 2026.05	-	-	-	22.2	15.2	25	48.3	26.2
EvolveR 2026.05	-	-	-	32.5	31.1	25	20.9	28
Mem0+GRPO 2026.05	-	-	-	36.5	22	40.6	23.1	29.5
SimpleMem+GRPO 2026.05	-	-	-	25.4	28	26.6	25.1	26.4
SkillRL 2026.05	-	-	-	36	34.2	41.4	49.3	38.3
SKILL0 2026.05	-	-	-	39.2	33	38.1	37.9	35.2
SLIM 2026.05	-	-	-	31.9	36.8	31.5	33	33.7
Skill0.5 2026.05	-	-	-	39.1	37.3	41.1	50.9	40.4