Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Citation Evaluation on HotpotQA
Loading...
61.8
Citation Recall
LongCite-9B
18.536
29.768
41
52.232
Sep 4, 2024
Citation Recall
Citation Precision
Citation F1
Updated 4d ago
Evaluation Results
Method
Method
Links
Citation Recall
Citation Precision
Citation F1
LongCite-9B
Strategy=LAC-S
2024.09
61.8
78.8
64.8
LongCite-8B
Strategy=LAC-S
2024.09
59.2
72.1
60.3
GPT-4o
Strategy=LAC-S
2024.09
55.7
62.3
53.4
GLM-4
Strategy=LAC-S
2024.09
47
50.1
44.4
Claude-3-sonnet
Strategy=LAC-S
2024.09
46.4
65.8
49.9
Mistral-Large-Instruct
Strategy=LAC-S
2024.09
34.5
40.9
32.1
Llama-3.1-70B-Instruct
Strategy=LAC-S
2024.09
29.6
37.3
28.6
GLM-4-9B-chat
Strategy=LAC-S
2024.09
22.9
28.8
20.1
Llama-3.1-8B-Instruct
Strategy=LAC-S
2024.09
20.2
30.9
20.9
Feedback
Search any
task
Search any
task