Skip to content

Benchmark

HF Hallucinations XSum, factKB

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

0.038
Mean
0.039
Median
0
Std dev
0.038
10th percentile
0.039
90th percentile
0.0379
Min

Leaderboard

#ModelScore
1Llama-2-13b-chat-hfclustermap_all/XSum, factKB· HF Hallucinations aggregate matrix0.0388
2Llama-2-7b-chat-hfclustermap_all/XSum, factKB· HF Hallucinations aggregate matrix0.0379

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