Delulu - Method Hallucination Detection: leaderboard
LLMs as judges on the 461 Delulu (2026) fill-in-the-middle samples whose hallucinated completion contains calls to methods that do not exist: the judge must accept the real completion and reject the hallucinated one. The score is the both-correct rate (%); higher is better.
Metric: Both-correct rate (%) on the 461 Delulu samples whose hallucination is calls to methods 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: Estimated already saturated. 8 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.5 | 94.6 | #165 |
| 2 | GPT-5.2 Codex | 92.7 | #186 |
| 3 | GPT-5.4 | 84.2 | #138 |
| 4 | Claude Sonnet 4.6 | 78.4 | #179 |
| 5 | GPT-5.4 Mini | 78.2 | #409 |
| 6 | Claude Haiku 4.5 | 77.1 | #587 |
| 7 | GPT-4.1 Mini | 73 | #799 |
| 8 | GPT-4o Mini | 54.6 | #1680 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=delulu-method-hallucination-detection · How It Works · Data refreshed daily, snapshot 2026-11-22.