Skip to content

Benchmark

HF Hallucinations TruthfulQA MC1, 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

0.291
Mean
0.302
Median
0.011
Std dev
0.28
10th percentile
0.302
90th percentile
0.28
Min

Leaderboard

#ModelScore
1Llama-2-7b-chat-hfclustermap_all/TruthfulQA MC1, Accuracy· HF Hallucinations aggregate matrix0.302
2Llama-2-13b-chat-hfclustermap_all/TruthfulQA MC1, Accuracy· HF Hallucinations aggregate matrix0.28

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