InteractWeb-Bench - Hallucination Rate: leaderboard
Metric: Hallucination rate (%): share of tasks where the agent builds on requirements the user never stated instead of asking, interactive website generation; lower is better. Source: arxiv.org. Saturation forecast: Not forecast. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4.1 Mini | 23.5 |
| 2 | Gemini 3.1 Flash Lite | 27.7 |
| 3 | GPT-4.1 | 31.7 |
| 4 | Qwen 3.5 9B | 53.7 |
| 5 | Qwen 3.5 397B A17B | 56.4 |
| 6 | Gemma 4 31B (IT) | 61.7 |
| 7 | Qwen 3.6 Plus | 62.4 |
| 8 | Kimi K2.5 | 64.1 |
| 9 | Gemma 4 26B A4B (IT) | 72.3 |
Interactive version: theaggregate.ai/benchmark?slug=interactweb-bench-hallucination-rate · How It Works · Data refreshed daily, snapshot 2026-10-07.