Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Multi-Hop Question Answering on HotpotQA (Accuracy)
Loading...
44.2
Accuracy
SkillOrchestra+
12.792
20.946
29.1
37.254
Feb 23, 2026
Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
SkillOrchestra+
Routing Strategy=Skill...
2026.02
44.2
SkillOrchestra
Routing Strategy=Skill...
2026.02
39
Router-R1
Routing Strategy=RL-ba...
2026.02
35.2
Largest LLM
Routing Strategy=Heuri...
2026.02
27.8
Prompt LLM
Routing Strategy=Heuri...
2026.02
26.8
RouterDC
Routing Strategy=Heuri...
2026.02
24.4
Search-R1
Routing Strategy=No Ro...
2026.02
23.6
GraphRouter
Routing Strategy=Heuri...
2026.02
23.4
FrugalGPT
Routing Strategy=Heuri...
2026.02
23.4
KNN Router
Routing Strategy=Heuri...
2026.02
22.4
RAG
Routing Strategy=No Ro...
2026.02
21.6
BERT Router
Routing Strategy=Heuri...
2026.02
21.6
Prompt LLM+
Routing Strategy=Heuri...
2026.02
20.6
SFT
Routing Strategy=No Ro...
2026.02
19.8
MLP Router
Routing Strategy=Heuri...
2026.02
19.8
CoT
Routing Strategy=No Ro...
2026.02
16.8
KNN Router+
Routing Strategy=Heuri...
2026.02
15.4
Vanilla
Routing Strategy=No Ro...
2026.02
14
Feedback
Search any
task
Search any
task