PhantomBench - Entities (Meaning): 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 what the concept means or refers to (presupposing it 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: Around December 2026. 16 models tracked.

Top models

#ModelScore
1Llama 3.1 8B Instruct7.92
2Qwen 2.5 7B Instruct8.33
3Qwen 3 14B9.92
4Qwen 3 8B15.92
5Gemma 2 9B (IT)20.42
6Qwen 3 32B23.5
7Qwen 3 4B24.33
8Gemini 2.5 Pro28.59
9Qwen 3 1.7B31
10Gemini 2.5 Flash33.67
11Mistral 7B Instruct (v0.3)47.83
12GPT-OSS-20B (Medium)57.7
13GPT-OSS-20B (Low)61.51
14DeepSeek R1 Distill Qwen 32B66.84
15Gemma 3 12B (IT)85.99

Interactive version: theaggregate.ai/benchmark?slug=phantombench-entities-meaning · How It Works · Data refreshed daily, snapshot 2026-09-29.