LexAgentHallu - ReAct - L2 Hallucination Density: leaderboard
Metric: Hallucination Density (%). Source: arxiv.org. Saturation forecast: Around December 2026. 5 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.4 | 24.2 |
| 2 | Gemini 3.1 Pro (Preview) | 24.7 |
| 3 | Qwen 3.5 27B | 25.1 |
| 4 | Qwen 3.6 27B | 25.1 |
| 5 | Qwen 3.5 9B | 34.5 |
Interactive version: theaggregate.ai/benchmark?slug=lexagenthallu-react-l2-hallucination-density · How It Works · Data refreshed daily, snapshot 2026-09-24.