Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-hop reasoning Knowledge Base Question Answering on WebQuestion
Loading...
86.02
Hit@1
KG-Reasoner
56.7752
64.3676
71.96
79.5524
Jun 2, 2025
Jul 24, 2025
Sep 15, 2025
Nov 7, 2025
Dec 29, 2025
Feb 20, 2026
Apr 14, 2026
Hit@1
Updated 4d ago
Evaluation Results
Method
Method
Links
Hit@1
KG-Reasoner
LLM=Qwen3, Size=30B
2026.04
86.02
PoG
LLM=GPT-4, Size=-
2026.04
84.7
KBQA-o1
LLM=LLaMA3, Size=70B
2026.04
82.5
iQUEST
Backbone=GPT-4o
2025.06
81.23
iQUEST
LLM=GPT-4o, Size=-
2026.04
81.2
LMP
LLM=GPT-4, Size=-
2026.04
80.4
KG-CoT
2025.06
68
ToG
2025.06
57.9
ToG
LLM=GPT-4, Size=-
2026.04
57.9
Feedback
Search any
task
Search any
task