Chronicles-OCR - Archaic Character Spotting: leaderboard
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. 29 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Seed 2.0 Pro (Non-reasoning) | 16.5 |
| 2 | Seed 2.0 Pro | 15.3 |
| 3 | Qwen 3.5 397B A17B (Non-reasoning) | 9.7 |
| 4 | Qwen 3 VL 235B A22B Instruct | 7.8 |
| 5 | Seed 1.8 | 7.4 |
| 6 | Qwen 3.5 35B A3B (Non-reasoning) | 5.6 |
| 7 | Kimi K2.5 (Non-reasoning) | 5 |
| 8 | Qwen 3 VL 8B Instruct | 3.4 |
| 9 | Gemini 3.1 Pro (Preview) | 2.6 |
| 10 | Gemma 4 31B (IT) | 2.3 |
| 11 | Qwen 3 VL 235B A22B (Thinking) | 2.1 |
| 12 | Kimi K2.5 | 1.8 |
| 13 | GLM-4.5V | 1.4 |
| 14 | Qwen 3 VL 8B (Thinking) | 1 |
| 15 | Gemini 2.5 Pro | 0.8 |
Interactive version: theaggregate.ai/benchmark?slug=chronicles-ocr-archaic-character-spotting · How It Works · Data refreshed daily, snapshot 2026-10-07.