Vision-language understanding on MMBench CN v1.1
87.7AccuracyQwen3-Omni
Evaluation results
| Method | Links | |
|---|---|---|
| Qwen3-OmniInference mode=Thinking mode, Size=30B-A3B2026.04 | 87.7 | |
| MiniCPM-o 4.5Inference mode=Thinking mode, Size=9B2026.04 | 87.6 | |
| Gemini 2.5 FlashInference mode=Thinking mode2026.04 | 87.3 | |
| GPT-5Inference mode=Thinking mode2026.04 | 85.6 | |
| Qwen3-VLInference mode=Thinking mode, Size=8B2026.04 | 85.5 |