Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Multi-hop Question Answering on HotpotQA (Avg@4)
Loading...
67.6
Avg@4
ASearcher-7B
50.752
55.126
59.5
63.874
Feb 4, 2026
Avg@4
Updated 4d ago
Evaluation Results
Method
Method
Links
Avg@4
ASearcher-7B
Setting=Single Agent
2026.02
67.6
WIDESEEK-R1-4B
Setting=Multi-Agent Sy...
2026.02
64.2
SingleSeek-R1-4B
Setting=Single Agent
2026.02
62.1
OWL-8B
Setting=Multi-Agent Sy...
2026.02
61
Search-R1-7B
Setting=Single Agent
2026.02
60.8
AgentFlow-7B
Setting=Multi-Agent Sy...
2026.02
57
Qwen3-4B
Setting=Multi-Agent Sy...
2026.02
54.3
MiroFlow-8B
Setting=Multi-Agent Sy...
2026.02
52.4
Qwen3-4B
Setting=Single Agent
2026.02
51.4
Feedback
Search any
task
Search any
task