Skip to content

Benchmark

HF Hallucinations XSum, BERT-P

Factuality benchmarks measure how often models get facts right. Higher scores are better.

Models measured
2
Scores recorded
2
Sources
1
IQ weight
No weight published

Score distribution

0.389
Mean
0.392
Median
0.003
Std dev
0.385
10th percentile
0.392
90th percentile
0.385
Min

Leaderboard

#ModelScore
1Llama-2-13b-chat-hfclustermap_all/XSum, BERT-P· HF Hallucinations aggregate matrix0.392
2Llama-2-7b-chat-hfclustermap_all/XSum, BERT-P· HF Hallucinations aggregate matrix0.385

Data credits: Hallucinations Leaderboard, Apache-2.0. Publisher-selected archived score matrix; native normalized fractions. (licence)