PhantomBench - Entities (Existence): leaderboard
Metric: Hallucination rate (%): share of answers that do not abstain on the Phantom-E subset (1,200 generated non-existent entities: events, holidays, elections, disasters, creative works and places), verified absent from the 2.3-trillion-token Dolma corpus, when the prompt asks whether the concept exists; a Gemini 2.5 Flash judge labels abstention; reasoning-model rates count only generations that reached a final answer; lower is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 16 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3 14B | 3.5 |
| 2 | GPT-OSS-20B (Medium) | 3.93 |
| 3 | Qwen 3 8B | 4 |
| 4 | Qwen 2.5 7B Instruct | 4.08 |
| 5 | GPT-OSS-20B (Low) | 4.68 |
| 6 | Gemma 2 9B (IT) | 7.16 |
| 7 | Llama 3.1 8B Instruct | 7.41 |
| 8 | Qwen 3 4B | 7.5 |
| 9 | Qwen 3 32B | 8 |
| 10 | Qwen 3 1.7B | 13.59 |
| 11 | DeepSeek R1 Distill Qwen 32B | 15.2 |
| 12 | Mistral 7B Instruct (v0.3) | 17.09 |
| 13 | Gemini 2.5 Flash | 22.25 |
| 14 | Gemini 2.5 Pro | 29.33 |
| 15 | Gemma 3 12B (IT) | 47.5 |
Interactive version: theaggregate.ai/benchmark?slug=phantombench-entities-existence · How It Works · Data refreshed daily, snapshot 2026-09-29.