Chronicles-OCR - Archaic Script Classification: leaderboard
Metric: Accuracy (%) of classifying the image into one of the Seven Chinese Scripts, on images of the archaic scripts (Oracle Bone, Bronze and Seal), the paper Average column over the per-script results; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 29 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Seed 1.8 | 96.7 |
| 2 | Seed 2.0 Pro | 96.6 |
| 3 | Kimi K2.5 (Non-reasoning) | 96.4 |
| 4 | Seed 2.0 Pro (Non-reasoning) | 95.9 |
| 5 | Kimi K2.5 | 94.7 |
| 6 | Gemini 3.1 Pro (Preview) | 93.8 |
| 7 | Qwen 3 VL 235B A22B Instruct | 91.8 |
| 8 | Claude Opus 4.7 (Thinking) | 90.4 |
| 9 | Qwen 3.5 397B A17B (Non-reasoning) | 88.3 |
| 10 | GPT-5 | 88.1 |
| 11 | MiMo-V2-Omni | 87.7 |
| 12 | Gemini 2.5 Pro | 87.5 |
| 13 | Qwen 3 VL 235B A22B (Thinking) | 87.3 |
| 14 | GPT-4o | 82 |
| 15 | GLM-4.5V | 76.8 |
Interactive version: theaggregate.ai/benchmark?slug=chronicles-ocr-archaic-script-classification · How It Works · Data refreshed daily, snapshot 2026-10-07.