Agent & Grounding on ScreenSpot V2
94.7ScoreGemini-3-Pro
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini-3-Pro2026.03 | 94.7 | |
| Intern-S1-ProNumber of Parameters=1T-A22B2026.03 | 93.6 | |
| Qwen3-VL-235B-ThinkingNumber of Parameters=235B-A22B, Thinking Configuration=true2026.03 | 92.8 | |
| Kimi-K2.5Number of Parameters=1T-A32B2026.03 | 92.4 | |
| GPT-5.22026.03 | 49.4 |