Visual Understanding on V* Bench
0.942Avg@8 EMSenseNova-MARS-32B
Evaluation results
| Method | Links | |
|---|---|---|
| SenseNova-MARS-32BMethod Category=Agentic Model2025.12 | 0.942 | |
| Qwen3-VL-235B-A22B-InstructMethod Category=Agentic Model2025.12 | 0.937 | |
| SenseNova-MARS-8BMethod Category=Agentic Model2025.12 | 0.922 | |
| Qwen3-VL-32B-InstructMethod Category=Agentic Model2025.12 | 0.911 | |
| Mini o3Method Category=Agentic Model2025.12 | 0.882 | |
| Skywork-R1V4Method Category=Agentic Model2025.12 | 0.88 | |
| Qwen3-VL-8B-InstructMethod Category=Direct Answer2025.12 | 0.864 | |
| Pixel-ReasonerMethod Category=Agentic Model2025.12 | 0.843 | |
| Gemini-2.5-ProMethod Category=Direct Answer2025.12 | 0.838 | |
| MonetMethod Category=Agentic Model2025.12 | 0.833 | |
| DeepEyesMethod Category=Agentic Model2025.12 | 0.833 | |
| ThymeMethod Category=Agentic Model2025.12 | 0.822 | |
| DeepEyesV2Method Category=Agentic Model2025.12 | 0.818 | |
| Qwen2.5-VL-32B-InstructMethod Category=Direct Answer2025.12 | 0.806 | |
| LLaVA-onevisonMethod Category=Direct Answer2025.12 | 0.754 | |
| Qwen2.5-VL-7B-InstructMethod Category=Direct Answer2025.12 | 0.753 | |
| SEALMethod Category=Agentic Model2025.12 | 0.748 | |
| GPT-4oMethod Category=Direct Answer2025.12 | 0.675 |