BLUFF - Veracity (English Prompt, Long-Tail): leaderboard
Metric: Macro-F1 (%) of zero-shot binary real/fake news classification (macro-F1, %) on the BLUFF test split, the decoder LLM answering with temperature 0.1 and at most 10 new tokens, with the English (cross-lingual) prompt, averaged over the 57 long-tail (low-resource) languages; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 7 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemma 3 1B (IT) | 42.7 | #1484 |
| 2 | Llama 3.2 1B Instruct | 38 | #1518 |
| 3 | Qwen 3 0.6B | 37.5 | #1440 |
| 4 | Gemma 3 270M (IT) | 27.3 | #1562 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=bluff-veracity-english-prompt-long-tail · How It Works · Data refreshed daily, snapshot 2026-10-11.