Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Web navigation on WebShop
Loading...
71.3
Average Score
IPR
15.764
30.182
44.6
59.018
Nov 27, 2025
Dec 1, 2025
Dec 5, 2025
Dec 9, 2025
Dec 13, 2025
Dec 17, 2025
Dec 22, 2025
Average Score
Normalized Reward
Updated 4d ago
Evaluation Results
Method
Method
Links
Average Score
Normalized Reward
IPR
Refinement Category=Pr...
2025.12
71.3
-
MACLA
Refinement Category=Pr...
2025.12
70.2
-
ETO
Refinement Category=Ou...
2025.12
67.4
-
Co-Evolving Agents
Backbone=Qwen3-4B-Inst...
2025.11
66.3
72.5
RFT-PPO
Refinement Category=Ou...
2025.12
64.2
-
Step-PPO
Refinement Category=Pr...
2025.12
64
-
RFT-CR
Refinement Category=Ou...
2025.12
63.6
-
GPT-4
Refinement Category=Pr...
2025.12
63.2
-
GPT-3.5-Turbo
Refinement Category=Pr...
2025.12
62.4
-
SFT
Refinement Category=Ou...
2025.12
60.2
-
ETO
Backbone=Qwen3-4B-Inst...
2025.11
59.5
65.7
SFT
Backbone=Qwen3-4B-Inst...
2025.11
40.3
63.9
Llama-2-7B
Refinement Category=Pr...
2025.12
17.9
-
Feedback
Search any
task
Search any
task