benchmark
.
space
benchmarks
rankings
compare
voices
transcripts
papers
articles
OmniDocBench leaderboard
OmniDocBench
5 models tested · Updated 2026-04-06 · Verified sources only
MinerU2.5-Pro
leads at
95.69%
1
MinerU2.5-Pro
Shanghai AI Lab ·
arxiv/2604.04771
· 2026-04-06
SOTA on OmniDocBench v1.6 via pure data engineering — no architecture changes. Expanded training from <10M to 65.5M samples.
95.69%
2
GLM-OCR
Zhipu AI ·
arxiv/2603.10910
· 2026-03-11
0.9B model (0.4B encoder + 0.5B decoder) achieves #1 on OmniDocBench v1.5. Outperforms models 260x larger including GPT-5.2 and Gemini-3 Pro.
94.62%
3
PaddleOCR-VL-1.5
Baidu ·
arxiv/2601.21957
· 2026-01-29
0.9B compact VLM with NaViT dynamic resolution. Best text and formula recognition scores despite minimal size. Also introduces Real5-OmniDocBench for real-world robustness.
94.5%
4
Qianfan-OCR
Baidu ·
arxiv/2603.13398
· 2026-03-11
End-to-end unified OCR model. Wins 6/8 benchmarks in its class. Strong chart reasoning capabilities.
93.12%
5
FireRed-OCR
FireRed AI ·
arxiv/2603.01840
· 2026-03-02
3-stage training: multi-task pre-alignment, specialized SFT, and GRPO RL with format constraints. Qwen3-VL backbone.
92.94%