Chronicles-OCR - Archaic Script Classification: leaderboard
Chronicles-OCR (2026) tests vision-language models on historical Chinese writing across the Seven Chinese Scripts, 2,800 expert-annotated images from Oracle Bone to Cursive. This board scores naming which of the seven scripts an Oracle Bone, Bronze or Seal image shows, as accuracy in percent averaged over the three scripts; higher is better.
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. 26 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Seed 1.8 | 96.7 | #252 | |
| 2 | Seed 2.0 Pro | 96.6 | #222 | |
| 3 | Kimi K2.5 | Non-reasoning | 96.4 | #266 |
| 4 | Gemini 3.1 Pro (Preview) | 93.8 | #99 | |
| 5 | Qwen 3 VL 235B A22B Instruct | 91.8 | #532 | |
| 6 | Claude Opus 4.7 | Thinking | 90.4 | #85 |
| 7 | Qwen 3.5 397B A17B | Non-reasoning | 88.3 | #264 |
| 8 | GPT-5 | 88.1 | #178 | |
| 9 | MiMo-V2-Omni | 87.7 | #465 | |
| 10 | Gemini 2.5 Pro | 87.5 | #276 | |
| 11 | Qwen 3 VL 235B A22B (Thinking) | 87.3 | #459 | |
| 12 | GPT-4o | 82 | #751 | |
| 13 | InternVL3.5-241B-A28B | 79 | #733 | |
| 14 | GLM-4.5V | 76.8 | #754 | |
| 15 | Qwen 3.5 35B A3B | Non-reasoning | 76.5 | #492 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=chronicles-ocr-archaic-script-classification · How It Works · Data refreshed daily, snapshot 2026-11-21.