OCR Benchmarking on OCRBench v2 (en/cn metrics)
62.6AccuracySigLIP2-g
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| SigLIP2-gTokens per frame/tile=256, TTFT (ms)=517.6, LLM Backbone=9B Nemotron2026.07 | 62.6 | — | — | — | |
| RADIO1DTokens per frame/tile=128, TTFT (ms)=373.2, LLM Backbone=9B Nemotron2026.07 | 61.5 | — | — | — | |
| RADIO1DTokens per frame/tile=256, TTFT (ms)=452.8, LLM Backbone=9B Nemotron2026.07 | 61.4 | — | — | — | |
| SigLIP2-SO400mTokens per frame/tile=256, TTFT (ms)=440.5, LLM Backbone=9B Nemotron2026.07 | 61.1 | — | — | — | |
| RADIO1DTokens per frame/tile=192, TTFT (ms)=380.4, LLM Backbone=9B Nemotron2026.07 | 60.9 | — | — | — | |
| C-RADIOv4-HTokens per frame/tile=256, TTFT (ms)=468.2, LLM Backbone=9B Nemotron2026.07 | 60.4 | — | — | — | |
| RADIO1DTokens per frame/tile=224, TTFT (ms)=410.2, LLM Backbone=9B Nemotron2026.07 | 60.2 | — | — | — | |
| RADIO1DTokens per frame/tile=64, TTFT (ms)=346.1, LLM Backbone=9B Nemotron2026.07 | 59.5 | — | — | — | |
| RADIO1DTokens per frame/tile=32, TTFT (ms)=335.1, LLM Backbone=9B Nemotron2026.07 | 55.4 | — | — | — | |
| RADIO1DTokens per frame/tile=8, TTFT (ms)=329.7, LLM Backbone=9B Nemotron2026.07 | 49.2 | — | — | — | |
| RADIO1DTokens per frame/tile=256, TTFT (ms)=452.8, LLM Backbone=9B Nemotron2026.07 | 42.2 | — | — | — | |
| RADIO1DTokens per frame/tile=224, TTFT (ms)=410.2, LLM Backbone=9B Nemotron2026.07 | 41.8 | — | — | — | |
| C-RADIOv4-HTokens per frame/tile=256, TTFT (ms)=468.2, LLM Backbone=9B Nemotron2026.07 | 41.5 | — | — | — | |
| SigLIP2-gTokens per frame/tile=256, TTFT (ms)=517.6, LLM Backbone=9B Nemotron2026.07 | 41 | — | — | — | |
| SigLIP2-SO400mTokens per frame/tile=256, TTFT (ms)=440.5, LLM Backbone=9B Nemotron2026.07 | 40.7 | — | — | — | |
| RADIO1DTokens per frame/tile=192, TTFT (ms)=380.4, LLM Backbone=9B Nemotron2026.07 | 40.2 | — | — | — | |
| RADIO1DTokens per frame/tile=128, TTFT (ms)=373.2, LLM Backbone=9B Nemotron2026.07 | 38.6 | — | — | — | |
| RADIO1DTokens per frame/tile=64, TTFT (ms)=346.1, LLM Backbone=9B Nemotron2026.07 | 35.2 | — | — | — | |
| RADIO1DTokens per frame/tile=1, TTFT (ms)=327.0, LLM Backbone=9B Nemotron2026.07 | 34.1 | — | — | — | |
| RADIO1DTokens per frame/tile=32, TTFT (ms)=335.1, LLM Backbone=9B Nemotron2026.07 | 34.1 | — | — | — | |
| PAPO_GSize=7B, Base model=Qwen2.5-VL2025.07 | 32.11 | — | — | — | |
| GRPOSize=7B, Base model=Qwen2.5-VL2025.07 | 31.17 | — | — | — | |
| RADIO1DTokens per frame/tile=8, TTFT (ms)=329.7, LLM Backbone=9B Nemotron2026.07 | 27.9 | — | — | — | |
| BaseSize=7B, Base model=Qwen2.5-VL2025.07 | 27.75 | — | — | — | |
| PAPO_GSize=3B, Base model=Qwen2.5-VL2025.07 | 27.22 | — | — | — | |
| GRPOSize=3B, Base model=Qwen2.5-VL2025.07 | 26.32 | — | — | — | |
| BaseSize=3B, Base model=Qwen2.5-VL2025.07 | 20.14 | — | — | — | |
| RADIO1DTokens per frame/tile=1, TTFT (ms)=327.0, LLM Backbone=9B Nemotron2026.07 | 15.2 | — | — | — | |
| AODModel=LLaVA-1.5-7B2026.05 | — | — | — | 27.2 | |
| AODModel=Qwen2.5-VL-7B2026.05 | — | — | — | 52.4 | |
| AODModel=InternVL3-8B2026.05 | — | — | — | 54.4 | |
| ASDModel=LLaVA-1.5-7B2026.05 | — | — | — | 23.6 | |
| ASDModel=Qwen2.5-VL-7B2026.05 | — | — | — | 49.2 | |
| ASDModel=InternVL3-8B2026.05 | — | — | — | 51.5 | |
| BaseModel=LLaVA-1.5-7B2026.05 | — | — | — | 16.8 | |
| BaseModel=Qwen2.5-VL-7B2026.05 | — | — | — | 46.7 | |
| BaseModel=InternVL3-8B2026.05 | — | — | — | 49 | |
| Gemini-2.5-flash2025.09 | — | 56 | 57.9 | — | |
| GPT-4o-2024-05-132025.09 | — | 55.8 | 57.6 | — | |
| LaV-CoTModel Scale=3B, Training/Optimization Strategy=SFT2025.09 | — | 55.2 | 57.6 | — | |
| LaV-CoTModel Scale=3B, Training/Optimization Strategy=SFT+GRPO2025.09 | — | 56.4 | 58.2 | — | |
| PruneHalModel=LLaVA-1.5-7B2026.05 | — | — | — | 20.2 | |
| PruneHalModel=Qwen2.5-VL-7B2026.05 | — | — | — | 48.9 | |
| PruneHalModel=InternVL3-8B2026.05 | — | — | — | 52.1 | |
| Qwen2.5-VLModel Scale=3B2025.09 | — | 52.1 | 54.3 | — | |
| Qwen2.5-VLModel Scale=7B2025.09 | — | 53.2 | 56.1 | — | |
| TruthPrIntModel=LLaVA-1.5-7B2026.05 | — | — | — | 25.1 | |
| TruthPrIntModel=Qwen2.5-VL-7B2026.05 | — | — | — | 50.1 | |
| TruthPrIntModel=InternVL3-8B2026.05 | — | — | — | 52.9 | |
| VASparseModel=LLaVA-1.5-7B2026.05 | — | — | — | 17.2 | |
| VASparseModel=Qwen2.5-VL-7B2026.05 | — | — | — | 48.5 | |
| VASparseModel=InternVL3-8B2026.05 | — | — | — | 48.7 | |
| VCDModel=LLaVA-1.5-7B2026.05 | — | — | — | 19.4 | |
| VCDModel=Qwen2.5-VL-7B2026.05 | — | — | — | 47.8 | |
| VCDModel=InternVL3-8B2026.05 | — | — | — | 49.1 |