Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Question Answering on QALD en (WikiData) v10 (test)
Loading...
83.73
Hits@1
KG-Reasoner with Qwen-2.5-7B
38.5108
50.2504
61.99
73.7296
Apr 14, 2026
Hits@1
Updated 3d ago
Evaluation Results
Method
Method
Links
Hits@1
KG-Reasoner with Qwen-2.5-7B
Size=7B, KG Integratio...
2026.04
83.73
GPT-4o-mini + KG
Size=–, KG Integration...
2026.04
72.86
LLaMA-3.3-70B + KG
Size=70B, KG Integrati...
2026.04
71.78
DeepSeek-R1-Distill-Llama-70B + KG
Size=70B, KG Integrati...
2026.04
66.1
Qwen-2.5-7B (SFT) + KG
Size=7B, KG Integratio...
2026.04
65.18
LLaMA-3.1-8B (SFT) + KG
Size=8B, KG Integratio...
2026.04
59.63
Qwen-2.5-7B + KG
Size=7B, KG Integratio...
2026.04
56.54
GPT-4o
Size=–, KG Integration...
2026.04
56.2
LLaMA-3.3-70B
Size=70B, KG Integrati...
2026.04
56
LLaMA-3.1-8B + KG
Size=8B, KG Integratio...
2026.04
55.73
ToG-2.0 (ICL)(GPT-3.5-turbo)
Size=-, KG Integration...
2026.04
54.1
ToG with GPT 4
Size=–, KG Integration...
2026.04
53.8
GPT-4o-mini
Size=–, KG Integration...
2026.04
51.98
ToG with GPT 3.5-Turbo
Size=–, KG Integration...
2026.04
50.2
DeepSeek-R1-Distill-Llama-70B
Size=70B, KG Integrati...
2026.04
43.1
Qwen-2.5-7B
Size=7B, KG Integratio...
2026.04
41.88
LLaMA-3.1-8B
Size=8B, KG Integratio...
2026.04
40.25
Feedback
Search any
task
Search any
task