Bio
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
Bio (test)
82.9LLM-Judge Score
105
Bio
75.2Accuracy
60
Bio
81LLM-Judge Score
59
BIO (test)
51Precision
44
Bio
74.02Accuracy
42
BIO
-0.129PCC
32
Bio (test)
83.1Accuracy
24
BIO dataset
93Factual Precision
24
bio (test)
90Marginal Coverage
19
Bio
84.3Few-Shot Accuracy
17
Bio FactScore
81.2FactScore
17
Bio poison @ Position 10, k=10 (test)
79.9Robustness Score (LLM-J)
15
Bio poison @ Position 1, k=10 (test)
79.3Rob. LLM-J Score
15
bio
33.9Pass Rate
14
Bio
100IRBO
13
Bio
0.191NPMI
13
Bio (test)
0.557NMI
13
bio D = 5, N = 50000, h* = 0.000567161 (rnd)
491Result (Scale 1)
10
BIO M (test)
80.1Macro F1
9
bio
90.57Coverage
8
BIO (test)
88.9FS Score
8
BIO
62.8Smatch
8
Bio
14.1Precision
6
Bio
69.8PIA RLLMJ Score
6
Bio
0.15MRR
6