Neo-Classic - Author Attribution (10-Shot): leaderboard
Metric: Accuracy (%; pick the pseudonymous author of a contemporary poem from four candidates, given ten example poems per candidate; 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 2033. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3 Max | 55 |
| 2 | GPT-4o | 40.4 |
| 3 | Gemini 2.5 Pro | 40 |
| 4 | DeepSeek V3.2 | 37.7 |
| 5 | Yi 1.5 34B Chat | 37 |
| 6 | Gemini 3 Pro (Preview) | 27 |
Interactive version: theaggregate.ai/benchmark?slug=neo-classic-author-attribution-10-shot · How It Works · Data refreshed daily, snapshot 2026-09-26.