HCSU - Stone Rubbings: leaderboard
Metric: Accuracy (%) on stone-rubbing (Bei) character images, 8-way controlled candidate selection: identify which of 8 calligraphers (1 correct, 7 distractors, each with a style description and reference image) wrote a target character image, temperature 0.1; chance 12.5; higher is better. Source: arxiv.org. Saturation forecast: Around 2029. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.2 | 35.32 |
| 2 | Claude Sonnet 4.5 | 34.26 |
| 3 | Qwen 3 VL 235B A22B Instruct | 34.1 |
| 4 | GPT-4o | 32.26 |
| 5 | Gemini 2.5 Pro | 31.49 |
| 6 | Qwen 2.5 VL 72B Instruct | 26.6 |
| 7 | Qwen 3 VL 30B A3B Instruct | 23.42 |
| 8 | Qwen 2.5 VL 7B Instruct | 21.27 |
Interactive version: theaggregate.ai/benchmark?slug=hcsu-stone-rubbings · How It Works · Data refreshed daily, snapshot 2026-09-29.