Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Retrieval-Augmented Generation on LOFT and ICR2 Combined
Loading...
74
Overall Score
GPT-4-turbo
23.04
36.27
49.5
62.73
Jan 14, 2025
Overall Score
Updated 4d ago
Evaluation Results
Method
Method
Links
Overall Score
GPT-4-turbo
RAG Setting=Oracle RAG
2025.01
74
Phi-3-7B-128K
RAG Setting=Oracle RAG
2025.01
73
Qwen-2-7B-32K
RAG Setting=Oracle RAG
2025.01
71
Mistral-2-7B-32K
RAG Setting=Oracle RAG
2025.01
70
LLaMA-3-instruct-8B
RAG Setting=Oracle RAG
2025.01
68
GPT-4-turbo
RAG Setting=Vanilla RAG
2025.01
65
Qwen-2-1.5B-32K
RAG Setting=Oracle RAG
2025.01
63
Phi-3-7B-128K
RAG Setting=Vanilla RAG
2025.01
57
Qwen-2-7B-32K
RAG Setting=Vanilla RAG
2025.01
53
GPT-4-turbo
RAG Setting=Closed-book
2025.01
51
Mistral-2-7B-32K
RAG Setting=Vanilla RAG
2025.01
50
LLaMA-3-instruct-8B
RAG Setting=Vanilla RAG
2025.01
45
Qwen-2-1.5B-32K
RAG Setting=Vanilla RAG
2025.01
39
Mistral-2-7B-32K
RAG Setting=Closed-book
2025.01
38
Phi-3-7B-128K
RAG Setting=Closed-book
2025.01
35
Qwen-2-7B-32K
RAG Setting=Closed-book
2025.01
31
LLaMA-3-instruct-8B
RAG Setting=Closed-book
2025.01
27
Qwen-2-1.5B-32K
RAG Setting=Closed-book
2025.01
25
Feedback
Search any
task
Search any
task