Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Question Answering on MuSiQue OOD (test)
Loading...
85.16
Exact Match (EM)
SkillFlow
37.216
49.663
62.11
74.557
May 13, 2026
Exact Match (EM)
F1 Score
Updated 19d ago
Evaluation Results
Method
Method
Links
Exact Match (EM)
F1 Score
SkillFlow
Method Type=Ours, Back...
2026.05
85.16
89.29
AgentFlow
Method Type=Agent+RL,...
2026.05
79.69
84.9
FlowSteer
Method Type=Agent+RL,...
2026.05
79.69
85.22
AFlow
Method Type=Search-bas...
2026.05
78.13
84.38
SkillRL
Method Type=Agent+RL,...
2026.05
75.78
81.38
v4-flash
Method Type=Baseline,...
2026.05
50.78
59.32
Qwen3.5
Method Type=GRPO, Back...
2026.05
42.2
50.3
Qwen3.5
Method Type=SFT, Backb...
2026.05
39.1
47.9
Qwen3.5
Method Type=Baseline,...
2026.05
39.06
47.79
Feedback
Search any
task
Search any
task
