Unified Multimodal Parsing on OmniParsingBench Document
87.01Perception ScoreGemini-3-Pro
Evaluation results
| Method | Links | |
|---|---|---|
| Gemini-3-Pro2026.03 | 87.01 | |
| Logics-Parsing-Omni2026.03 | 84.9 | |
| Qwen3-VL-235B-A22BParameters=235B-A22B2026.03 | 84.47 | |
| Qwen3.5-397B-A17BParameters=397B-A17B2026.03 | 81.09 | |
| Qwen3-VL-30B-A3BParameters=30B-A3B2026.03 | 78.94 | |
| GPT-5.22026.03 | 77.43 | |
| Qwen3-Omni-30B-A3BParameters=30B-A3B2026.03 | 73.5 |