Visual Perception on Blink 41 (val)
87.4ScoreGemini 3 Pro
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini 3 ProModel Category=API call only2026.01 | 87.4 | |
| Gemini 2.5 ProModel Category=API call only2026.01 | 73.7 | |
| Gemini 2.5 FlashModel Category=API call only2026.01 | 70.2 | |
| Qwen3-VL-8BModel Category=Open weights only2026.01 | 69.1 | |
| GPT-5 miniModel Category=API call only2026.01 | 68.7 | |
| GPT-5Model Category=API call only2026.01 | 66.5 | |
| Qwen3-VL-4BModel Category=Open weights only2026.01 | 65.8 | |
| GLM-4.1V-9BModel Category=Open weights only2026.01 | 65.1 | |
| Claude Sonnet 4.5Model Category=API call only2026.01 | 64.8 | |
| InternVL3.5-8BModel Category=Open weights only2026.01 | 59.5 | |
| InternVL3.5-4BModel Category=Open weights only2026.01 | 58.1 | |
| Molmo2-4BModel Category=Molmo2 family2026.01 | 57.5 | |
| PLM-8BModel Category=Open models2026.01 | 56 | |
| PLM-3BModel Category=Open models2026.01 | 55.4 | |
| Keye-VL-1.5-8BModel Category=Open weights only2026.01 | 54.9 | |
| Molmo2-8BModel Category=Molmo2 family2026.01 | 51.3 | |
| Molmo2-O-7BModel Category=Molmo2 family2026.01 | 50.5 | |
| Eagle2.5-8BModel Category=Open weights only2026.01 | 45.8 | |
| MiniCPM-V-4.5-8BModel Category=Open weights only2026.01 | 42 |