Vision-language capability on MMVet
81.2ScoreGemini 2.5 Flash
Evaluation results
| Method | Links | |
|---|---|---|
| Gemini 2.5 FlashInference mode=Thinking mode2026.04 | 81.2 | |
| GPT-5Inference mode=Thinking mode2026.04 | 77.6 | |
| Qwen3-OmniInference mode=Thinking mode, Size=30B-A3B2026.04 | 74.8 | |
| MiniCPM-o 4.5Inference mode=Thinking mode, Size=9B2026.04 | 73.6 | |
| Qwen3-VLInference mode=Thinking mode, Size=8B2026.04 | 69.8 |