DelistBench (Closed-Book): leaderboard
Metric: Overall joint accuracy within 7 days (%; all 1,200 security-level delisting records: a Category A record needs the correct positive status, the announcement date within seven days and the broad reason, Category B and C records a correct negative status; invalid outputs and abstentions count as errors; closed-book, no web access). Source: arxiv.org. Saturation forecast: Around April 2028. 5 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.6 Flash | 70.6 |
| 2 | Gemini 3.5 Flash Lite (Medium) | 66.5 |
| 3 | DeepSeek V4 Flash (Non-reasoning) | 62.6 |
| 4 | GPT-5.6 Luna (Low) | 57.2 |
| 5 | DeepSeek V4 Pro (High) | 56.7 |
Interactive version: theaggregate.ai/benchmark?slug=delistbench-closed-book · How It Works · Data refreshed daily, snapshot 2026-09-26.