AuthorityBench - Fabricated Citations on True Claims: leaderboard
Metric: Hallucination rate (%) on true claims presented with a fabricated citation (TC x FC condition): share of non-refused responses a Qwen3-8B judge labels hallucinated (the model denies or distorts the true claim); 15K stratified subset for four models, full dataset for Gemma 3 4B, Llama 3.1 8B Instruct and Phi-4 Mini Instruct; lower is better. Source: arxiv.org. Saturation forecast: Around November 2027. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek V3.2 | 16.28 |
| 2 | Gemma 4 31B | 22.73 |
| 3 | Gemma 3 4B | 24.14 |
| 4 | GPT-5.4 Mini | 37.27 |
| 5 | Phi-4 Mini Instruct | 40.63 |
| 6 | Llama 3.1 8B Instruct | 43.76 |
| 7 | Claude Haiku 4.5 | 47.11 |
Interactive version: theaggregate.ai/benchmark?slug=authoritybench-fabricated-citations-on-true-claims · How It Works · Data refreshed daily, snapshot 2026-09-29.