Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Interactive Decision Making on WebShop (val)
Loading...
85.8
Score
GiGPO
20.592
37.521
54.45
71.379
Jul 5, 2026
Score
Success Rate
Updated 18d ago
Evaluation Results
Method
Method
Links
Score
Success Rate
GiGPO
Type=RL-based
2026.07
85.8
67.6
ProGPO
Type=RL-based
2026.07
85.4
71.5
HGPO
Type=RL-based
2026.07
83.2
65.6
GRPO
Type=RL-based
2026.07
81.9
56.8
RLOO
Type=RL-based
2026.07
73.9
52.1
PPO
Type=RL-based
2026.07
73.8
51.5
Reflexion
Type=Prompt-based
2026.07
55.8
21.9
Gemini-2.5-Pro
Type=Prompt-based
2026.07
42.5
35.9
ReAct
Type=Prompt-based
2026.07
40.1
11.3
GPT-4o
Type=Prompt-based
2026.07
31.8
23.7
Qwen2.5
Type=Prompt-based
2026.07
23.1
5.2
Feedback
Search any
task
Search any
task
