MultiWikiQHalluA - German: leaderboard
Faithfulness hallucination in German reading-comprehension answers (MultiWikiQHalluA, 2026): the share of 1,000 MultiWikiQA test answers in which a fine-tuned mmBERT-small LettuceDetect token classifier flags at least one token as unsupported by the Wikipedia context. Percent of answers; lower is better.
Metric: Answer-level hallucination rate (%): share of the 1,000 German MultiWikiQA test answers in which the fine-tuned mmBERT-small LettuceDetect token classifier flags at least one token as unsupported by the Wikipedia context, times 100; lower is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 5 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3 14B | 4 | #1269 |
| 2 | Gemma 3 12B (IT) | 6 | #1887 |
| 3 | cogito-v1-preview-qwen-32B | 6 | #1181 |
| 4 | cogito-v1-preview-llama-70B | 6 | #927 |
| 5 | Qwen 3 0.6B | 17 | #8350 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=multiwikiqhallua-german · How It Works · Data refreshed daily, snapshot 2026-11-21.