DoRA (Defense Documents) - Hallucination (GTE Retrieval): leaderboard
DoRA (2026) builds a retrieval-augmented question answering benchmark from defense-related documents, with test questions in five intent styles and auditable evidence. RAGEval keypoint hallucination rate in percent with GTE-retrieved passages as context, judged by an LLM; lower is better.
Metric: RAGEval keypoint hallucination rate (%) of grounded answers to the 1,259-question DoRA defense-document test split with the top-3 passages retrieved by GTE (gte-multilingual-base) as context: per-question share of the reference answer's keypoints the answer addresses incorrectly, judged by GPT-4o-mini and averaged over questions; lower is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 8 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-3.5 Turbo | 3.71 | #3005 |
| 2 | Llama 3.1 8B Instruct | 4.44 | #4600 |
| 3 | Qwen 2.5 7B Instruct | 4.65 | #2723 |
| 4 | Ministral-8B-Instruct-2410 | 4.7 | #4555 |
| 5 | GPT-4o Mini | 4.92 | #1667 |
| 6 | Llama 3 8B Instruct | 5.24 | #4852 |
| 7 | GPT-4o | 5.6 | #751 |
| 8 | Claude 3.5 Haiku | 5.87 | #1580 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=dora-defense-documents-hallucination-gte-retrieval · How It Works · Data refreshed daily, snapshot 2026-11-21.