Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Web-based Agent Reasoning on WebWalkerQA Medium
Loading...
72.86
Pass@3
ExpSeek
57.6032
61.5641
65.525
69.4859
Jan 13, 2026
Pass@3
Updated 4d ago
Evaluation Results
Method
Method
Links
Pass@3
ExpSeek
Base Model=Qwen3-32B
2026.01
72.86
ExpSeek
Base Model=Qwen3-8B
2026.01
72.45
REASONINGBANK+
Base Model=Qwen3-32B
2026.01
64.33
Training-Free GRPO
Base Model=Qwen3-8B
2026.01
62.54
No Experience
Base Model=Qwen3-32B
2026.01
61.43
No Experience
Base Model=Qwen3-8B
2026.01
60
Training-Free GRPO
Base Model=Qwen3-32B
2026.01
59.57
REASONINGBANK+
Base Model=Qwen3-8B
2026.01
58.19
Feedback
Search any
task
Search any
task