Skip to content

Benchmark

HF Hallucinations TriviaQA (8-shot), EM

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

0.093
Mean
0.098
Median
0.005
Std dev
0.088
10th percentile
0.098
90th percentile
0.0883
Min

Leaderboard

#ModelScore
1Llama-2-13b-chat-hfclustermap_all/TriviaQA (8-shot), EM· HF Hallucinations aggregate matrix0.0979
2Llama-2-7b-chat-hfclustermap_all/TriviaQA (8-shot), EM· HF Hallucinations aggregate matrix0.0883

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