Chronicles-OCR - Archaic Character Spotting: 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 end-to-end spotting on the Oracle Bone, Bronze and Seal scripts: the model must box every archaic character and give its modern equivalent, scored as text-spotting H-mean (0 to 100) averaged over the three scripts; higher is better.
Metric: Text-spotting H-mean (0-100) of predicted character boxes with their modern character mapping (a hit needs IoU above 0.75 and an exact character match, undeciphered symbols excluded) on 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: Not forecast. 26 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Seed 2.0 Pro | Non-reasoning | 16.5 | #222 |
| 2 | Qwen 3.5 397B A17B | Non-reasoning | 9.7 | #264 |
| 3 | Seed 1.8 | Non-reasoning | 9.2 | #252 |
| 4 | Qwen 3 VL 235B A22B Instruct | 7.8 | #532 | |
| 5 | Qwen 3.5 35B A3B | Non-reasoning | 5.6 | #492 |
| 6 | Kimi K2.5 | Non-reasoning | 5 | #266 |
| 7 | Qwen 3 VL 8B Instruct | 3.4 | #1029 | |
| 8 | Gemini 3.1 Pro (Preview) | 2.6 | #99 | |
| 9 | Gemma 4 31B (IT) | 2.3 | #350 | |
| 10 | Qwen 3 VL 235B A22B (Thinking) | 2.1 | #459 | |
| 11 | Qwen 3 VL 2B Instruct | 2.1 | #2367 | |
| 12 | Ovis2.6-30B-A3B | Thinking | 1.9 | |
| 13 | GLM-4.5V | 1.4 | #754 | |
| 14 | Qwen 3 VL 8B (Thinking) | 1 | #910 | |
| 15 | Gemini 2.5 Pro | 0.8 | #276 |
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-character-spotting · How It Works · Data refreshed daily, snapshot 2026-11-21.