Neo-Classic - Word Cloze (Random Distractors): leaderboard
Metric: Accuracy (%; restore a masked two-character word in a contemporary poem from four tone-consistent candidates sampled without part-of-speech linkage; 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 | Qwen 3 Max | 69 |
| 2 | DeepSeek V3.2 | 65.4 |
| 3 | GPT-4o | 57.3 |
| 4 | Gemini 2.5 Pro | 57 |
| 5 | Yi 1.5 34B Chat | 53 |
| 6 | Gemini 3 Pro (Preview) | 39 |
Interactive version: theaggregate.ai/benchmark?slug=neo-classic-word-cloze-random-distractors · How It Works · Data refreshed daily, snapshot 2026-09-26.