HoVer
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
HoVer (test)
73.1Accuracy
31
HOVER 4-hop (test)
66.23Macro F1
16
HOVER 3-hop (test)
66.42Macro F1
16
HOVER 2-hop (test)
75.13Macro F1
16
HoVer Refined
82.9Macro F1
14
HOVER
71.82Macro F1 (2-hop)
12
HOVER 4-hop
73.62Accuracy
12
HOVER 3-hop
75.16Accuracy
12
HOVER 2-hop
76.69Accuracy
12
HoVer 4-HOP
71.5Recall@100
8
HoVer
1,255LLM Throughput (token/s)
8
HoVer + LangChain
76.15Latency (s)
8
HOVER (test)
56.6AUROC
8
HoVer (test)
63.2Recall
7
HoVer 4-Hop
63Macro-F1
7
HoVer 3-Hop
58Macro F1
7
HoVer 2-Hop
71Macro F1
7
HoVer
0.768Recall@5
7
HoVer
71Accuracy
6
HoVer
66Correctness
5
HoVer
5,252Max System Prompt Tokens
4
HoVer (test)
79.4Accuracy (Test)
4
Hover
52.33Score
4
HoVer (val)
42Score (%)
4
HoVer few-shot
56Recall
4