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

Web navigation on WebShop

90.5Average Score

SAPO

Updated 1mo ago

Evaluation Results

Method
SAPO 2026.06	90.5	-	78.1
SKILLRL 2026.06	85.2	-	72.7
D2Skill 2026.06	83.4	-	73.4
Skill0 2026.06	83.2	-	71.9
RLOO* 2026.06	80.3	-	65.7
GRPO* 2026.06	79.3	-	66.1
IPR 2025.12	71.3	-	-
Q-Evolve 2026.06	70.5	-	-
QLASS 2026.06	70.3	-	-
MACLA 2025.12	70.2	-	-
DMPO 2026.06	70.1	-	-
Best-of-N 2026.06	67.9	-	-
SimpleMem+GRPO 2026.06	67.8	-	46.9
ETO 2025.12	67.4	-	-
ETO 2026.06	67.4	-	-
Co-Evolving Agents 2025.11	66.3	72.5	-
RFT-PPO 2025.12	64.2	-	-
Reflexion 2026.06	64.2	-	-
PPO 2026.06	64.2	-	-
Step-PPO 2025.12	64	-	-
RFT-CR 2025.12	63.6	-	-
RFT 2026.06	63.6	-	-
GPT-4 2025.12	63.2	-	-
GPT-4 2026.06	63.2	-	-
SFT 2026.06	63.1	-	-
GPT-3.5-Turbo 2025.12	62.4	-	-
GPT-3.5-Turbo 2026.06	62.4	-	-
SFT 2025.12	60.2	-	-
ETO 2025.11	59.5	65.7	-
Reflexion* 2026.06	58.1	-	28.8
Mem0+GRPO 2026.06	58.1	-	37.5
ReAct* 2026.06	46.2	-	19.5
Gemini-2.5-Pro 2026.06	42.5	-	35.9
EvolveR 2026.06	42.5	-	17.6
SFT 2025.11	40.3	63.9	-
SimpleMem 2026.06	33.2	-	8.59
GPT-4o 2026.06	31.8	-	23.7
ExpeL 2026.06	30.9	-	11.2
MemRL 2026.06	29.5	-	9.2
Qwen2.5 2026.06	26.4	-	7.8
MemP 2026.06	25.3	-	6.4
Mem0 2026.06	23.9	-	2
InternVL2.5-8B 2026.05	23.5	-	3.9
Qwen2.5-VL-7B 2026.05	19.4	-	4.1
Llama-2-7B 2025.12	17.9	-	-
Base Agent 2026.06	17.9	-	-
InternVL2.5-8B 2026.05	16.5	-	8.8
GPT-4o 2026.05	15.5	-	17.2
ViGoRL 2026.05	13.4	-	5.6
Qwen2.5-VL-7B 2026.05	12.7	-	11.2
SCALE-20k 2026.05	10.1	-	2.1
Qwen2.5-VL-7B 2026.05	8.5	-	18.3
InternVL2.5-8B 2026.05	6.6	-	11.6
SCALE 2026.05	5.7	-	14.4
SCALE 2026.05	4.9	-	11
Qwen3-4B 2026.05	-	9.6	1.5
Qwen3-8B 2026.05	-	10.3	2
Qwen3-30B-A3B 2026.05	-	25.6	3
Gemini-2.5-flash 2026.05	-	48.7	41.2
Gemini-3-Flash 2026.05	-	57.3	53
GRPO 2026.05	-	81.8	63.5
GSPO 2026.05	-	82.1	65
ScalingInter 2026.05	-	84.7	66.5
MATPO 2026.05	-	82.4	65
Critique-GRPO 2026.05	-	87.1	72.5
ICRL 2026.05	-	88.9	74.5
GRPO 2026.05	-	83.7	71.5
GSPO 2026.05	-	83.4	71
ScalingInter 2026.05	-	86.2	73
MATPO 2026.05	-	81.6	68
Critique-GRPO 2026.05	-	86.8	73.5
ICRL 2026.05	-	88.3	76
Augvis 2026.05	-	-	4.3
InternVL2.5-8B 2026.05	-	-	3
Qwen2.5-VL-7B 2026.05	-	-	4.1
LLaVA-NeXT-8B 2026.05	-	-	0