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
| # | Model | Score |
|---|---|---|
| 1 | Llama-2-13b-chat-hfclustermap_all/XSum, factKB· HF Hallucinations aggregate matrix | 0.0388 |
| 2 | Llama-2-7b-chat-hfclustermap_all/XSum, factKB· HF Hallucinations aggregate matrix | 0.0379 |
Data credits: Hallucinations Leaderboard, Apache-2.0. Publisher-selected archived score matrix; native normalized fractions. (licence)