Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Agentic Search on MuSiQue
Loading...
24.2
LJFT Score
Laser
3.4
8.8
14.2
19.6
Dec 23, 2025
LJFT Score
LLMJ Score
Accuracy
Updated 3d ago
Evaluation Results
Method
Method
Links
LJFT Score
LLMJ Score
Accuracy
Laser
Base Model=Qwen3-32B
2025.12
24.2
31.6
22
Laser
Base Model=Qwen3-8B
2025.12
22.4
28.2
20.4
ReAct
Base Model=Qwen3-32B
2025.12
22
26.8
15.2
ReAct
Base Model=Qwen3-8B
2025.12
19.4
24.6
14.6
Search-R1
Base Model=Qwen3-32B
2025.12
17.6
22.2
11.4
RAG
Base Model=Qwen3-32B
2025.12
12.2
14
10
Thinking
Base Model=Qwen3-32B
2025.12
10.6
14
7.8
Search-R1
Base Model=Qwen3-8B
2025.12
10.4
14.6
7.6
RAG
Base Model=Qwen3-8B
2025.12
9
10.8
7.4
No-thinking
Base Model=Qwen3-32B
2025.12
7.8
11.2
5.8
Thinking
Base Model=Qwen3-8B
2025.12
5.8
8.6
3.4
No-thinking
Base Model=Qwen3-8B
2025.12
4.2
6
3
Feedback
Search any
task
Search any
task