Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-Hop Question Answering on 2wiki (F1 score)
Loading...
61.3
F1 Score
ReCal
16.996
28.498
40
51.502
Jun 10, 2026
F1 Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
F1 Score
ReCal
Routing=RL-based Routing
2026.06
61.3
ReCal
Routing=RL-based Routi...
2026.06
61.3
Router-R1
Routing=RL-based Routing
2026.06
52.9
Largest LLM
Routing=Heuristic & Di...
2026.06
39.7
Prompt LLM
Routing=Heuristic & Di...
2026.06
39.3
Prompt LLM*
Routing=Heuristic & Di...
2026.06
35.5
Search-R1
Routing=No Routing
2026.06
31.7
Vanilla
Routing=No Routing
2026.06
30.4
KNN Router*
Routing=Heuristic & Di...
2026.06
29.9
RouterDC
Routing=Heuristic & Di...
2026.06
29.3
SFT
Routing=No Routing
2026.06
29.1
KNN Router
Routing=Heuristic & Di...
2026.06
28.9
RouteLLM
Routing=Heuristic & Di...
2026.06
28.4
MLP Router
Routing=Heuristic & Di...
2026.06
27.7
GraphRouter
Routing=Heuristic & Di...
2026.06
25.8
CoT
Routing=No Routing
2026.06
25.1
RAG
Routing=No Routing
2026.06
18.7
Feedback
Search any
task
Search any
task