Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Retrieval-Augmented Question Answering on 170 unique canonical user-facing queries Simple Rec. n=50
Loading...
96
Faithfulness
GPT-5.5
64.8
72.9
81
89.1
Jun 14, 2026
Faithfulness
Recall@10
Correctness
Completeness
Updated 1mo ago
Evaluation Results
Method
Method
Links
Faithfulness
Recall@10
Correctness
Completeness
GPT-5.5
2026.06
96
-
60
57
GPT-4o
2026.06
95
-
48
50
Qwen2.5
2026.06
94
-
37
44
I-GUIDE SS
mode=Smart Search
2026.06
75
63
76
70
Naive RAG
2026.06
67
17
30
23
Claude Opus 4.7
2026.06
66
-
43
35
Feedback
Search any
task
Search any
task