Skip to content

Benchmark

HF Hallucinations CNN/DM, ROUGE-L

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

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

Score distribution

0.01
Mean
0.01
Median
0
Std dev
0.01
10th percentile
0.01
90th percentile
0.0104
Min

Leaderboard

#ModelScore
1Llama-2-7b-chat-hfclustermap_all/CNN/DM, ROUGE-L· HF Hallucinations aggregate matrix0.0104

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