Neo-Classic - Author Attribution (3-Shot, CoT): leaderboard
Metric: Accuracy (%; pick the pseudonymous author of a contemporary poem from four candidates, given three example poems per candidate and a prompt to summarise each style first; accuracy on a 100-question sample of the task, as reported in the paper's full results table (accuracy@IF); temperature 0.1, top-p 0.9). Source: arxiv.org. Saturation forecast: Around 2030. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro (Preview) | 36 |
| 2 | DeepSeek V3.2 | 34.3 |
| 3 | GPT-4o | 34 |
| 4 | Qwen 3 Max | 34 |
| 5 | Gemini 2.5 Pro | 28 |
| 6 | Yi 1.5 34B Chat | 22 |
Interactive version: theaggregate.ai/benchmark?slug=neo-classic-author-attribution-3-shot-cot · How It Works · Data refreshed daily, snapshot 2026-09-26.