LLMTabBench (16-Shot) - Classic Datasets: leaderboard
Metric: ROC-AUC (0-1; 16 labelled demonstrations; 24 classic OpenML and Kaggle binary classification datasets; generation mode, prompt with column names and task description; mean over datasets and five demonstration draws). Source: arxiv.org. Saturation forecast: Estimated already saturated. 4 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3 14B | 0.78 |
| 2 | Qwen 3 8B | 0.78 |
| 3 | GPT-4o Mini | 0.77 |
| 4 | Qwen 3 1.7B | 0.69 |
Interactive version: theaggregate.ai/benchmark?slug=llmtabbench-16-shot-classic-datasets · How It Works · Data refreshed daily, snapshot 2026-09-26.