Delulu - Import Hallucination Detection: leaderboard
Metric: Both-correct rate (%) on the 478 Delulu samples whose hallucination is imports of packages that do not exist, as an LLM judge: the judge sees each sample twice, once with the gold completion and once with the hallucinated one, and must accept the first and reject the second (both-correct rate, %), with chain-of-thought and a binary verdict; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.5 | 83.4 |
| 2 | Claude Sonnet 4.6 | 80.3 |
| 3 | GPT-5.2 Codex | 75.4 |
| 4 | GPT-5.4 Mini | 69.2 |
| 5 | GPT-5.4 | 67.9 |
| 6 | Claude Haiku 4.5 | 65.6 |
| 7 | GPT-4.1 Mini | 56.9 |
| 8 | GPT-4o Mini | 48.7 |
Interactive version: theaggregate.ai/benchmark?slug=delulu-import-hallucination-detection · How It Works · Data refreshed daily, snapshot 2026-10-07.