Skip to content

Benchmark

HF Hallucinations True-False, Accuracy

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

0.827
Mean
0.851
Median
0.025
Std dev
0.802
10th percentile
0.851
90th percentile
0.802
Min

Leaderboard

#ModelScore
1Llama-2-13b-chat-hfclustermap_all/True-False, Accuracy· HF Hallucinations aggregate matrix0.851
2Llama-2-7b-chat-hfclustermap_all/True-False, Accuracy· HF Hallucinations aggregate matrix0.802

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