Dr. DocBench - Formula CDM: leaderboard
Metric: Character Detection Matching score of display formulas (0-100), 4,514 expert-annotated difficult pages sampled by parser failure from long books in 52 subject domains; each page parsed with the model's own document-to-markdown prompt (specialized parsers through their official APIs); higher is better. Source: arxiv.org. Saturation forecast: Around 2030. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o | 36.02 |
| 2 | Qwen 3.5 Flash | 35.69 |
| 3 | GPT-5.5 | 34.55 |
| 4 | Qwen 3.5 122B A10B | 32.54 |
| 5 | Gemini 3.1 Pro (Preview) | 32.22 |
| 6 | Claude Opus 4.6 | 32.02 |
| 7 | Qwen 3.5 Plus | 30.4 |
| 8 | Kimi K2.5 | 27.04 |
| 9 | Nemotron Nano 12B v2 VL | 12.82 |
Interactive version: theaggregate.ai/benchmark?slug=dr-docbench-formula-cdm · How It Works · Data refreshed daily, snapshot 2026-09-29.