Choice Probability Prediction on Visual Persuasion Pooled Tasks 1.0
0.764Mean Probability EstimateGPT-4o
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-4oStrategy=VFD, Evaluation Status=Final2026.02 | 0.764 | |
| Qwen-VL 235BStrategy=VFD, Evaluation Status=Final2026.02 | 0.758 | |
| Gemini 3 FlashStrategy=VFD, Evaluation Status=Final2026.02 | 0.741 | |
| Llama 4 MaverickStrategy=VFD, Evaluation Status=Final2026.02 | 0.736 | |
| Qwen-VL 235BStrategy=CVPO, Evaluation Status=Final2026.02 | 0.734 | |
| Gemini 3 ProStrategy=VFD, Evaluation Status=Final2026.02 | 0.732 | |
| Claude Haiku 4.5Strategy=VFD, Evaluation Status=Final2026.02 | 0.73 | |
| GPT-5 MiniStrategy=VFD, Evaluation Status=Final2026.02 | 0.724 | |
| Gemini 3 FlashStrategy=CVPO, Evaluation Status=Final2026.02 | 0.723 | |
| GPT-4oStrategy=CVPO, Evaluation Status=Final2026.02 | 0.715 | |
| Gemini 3 ProStrategy=CVPO, Evaluation Status=Final2026.02 | 0.706 | |
| Llama 4 MaverickStrategy=CVPO, Evaluation Status=Final2026.02 | 0.702 | |
| GPT-5 MiniStrategy=CVPO, Evaluation Status=Final2026.02 | 0.699 | |
| GPT-5.2Strategy=VFD, Evaluation Status=Final2026.02 | 0.687 | |
| Claude Haiku 4.5Strategy=VTG, Evaluation Status=Final2026.02 | 0.684 | |
| Claude Sonnet 4.5Strategy=VFD, Evaluation Status=Final2026.02 | 0.679 | |
| Claude Haiku 4.5Strategy=CVPO, Evaluation Status=Final2026.02 | 0.679 | |
| Claude Sonnet 4.5Strategy=CVPO, Evaluation Status=Final2026.02 | 0.677 | |
| Gemini 3 ProStrategy=VTG, Evaluation Status=Final2026.02 | 0.676 | |
| Gemini 3 FlashStrategy=VTG, Evaluation Status=Final2026.02 | 0.675 | |
| GPT-5.2Strategy=CVPO, Evaluation Status=Final2026.02 | 0.673 | |
| GPT-4oStrategy=VTG, Evaluation Status=Final2026.02 | 0.671 | |
| GPT-5 MiniStrategy=VTG, Evaluation Status=Final2026.02 | 0.668 | |
| Qwen-VL 235BStrategy=VTG, Evaluation Status=Final2026.02 | 0.666 | |
| Claude Sonnet 4.5Strategy=VTG, Evaluation Status=Final2026.02 | 0.661 | |
| Llama 4 MaverickStrategy=VTG, Evaluation Status=Final2026.02 | 0.652 | |
| GPT-5.2Strategy=VTG, Evaluation Status=Final2026.02 | 0.646 | |
| Qwen-VL 235BStrategy=VTG, Evaluation Status=Zero-shot2026.02 | 0.61 | |
| GPT-4oStrategy=VTG, Evaluation Status=Zero-shot2026.02 | 0.594 | |
| GPT-5.2Strategy=VTG, Evaluation Status=Zero-shot2026.02 | 0.575 | |
| Llama 4 MaverickStrategy=VTG, Evaluation Status=Zero-shot2026.02 | 0.575 | |
| Qwen-VL 235BStrategy=CVPO, Evaluation Status=Zero-shot2026.02 | 0.571 | |
| Claude Haiku 4.5Strategy=VTG, Evaluation Status=Zero-shot2026.02 | 0.57 | |
| GPT-5 MiniStrategy=VTG, Evaluation Status=Zero-shot2026.02 | 0.57 | |
| GPT-5.2Strategy=CVPO, Evaluation Status=Zero-shot2026.02 | 0.568 | |
| GPT-4oStrategy=CVPO, Evaluation Status=Zero-shot2026.02 | 0.565 | |
| Claude Haiku 4.5Strategy=CVPO, Evaluation Status=Zero-shot2026.02 | 0.564 | |
| GPT-5 MiniStrategy=CVPO, Evaluation Status=Zero-shot2026.02 | 0.561 | |
| Claude Haiku 4.5Strategy=VFD, Evaluation Status=Zero-shot2026.02 | 0.559 | |
| GPT-5.2Strategy=VFD, Evaluation Status=Zero-shot2026.02 | 0.557 | |
| Gemini 3 FlashStrategy=VTG, Evaluation Status=Zero-shot2026.02 | 0.549 | |
| Llama 4 MaverickStrategy=CVPO, Evaluation Status=Zero-shot2026.02 | 0.544 | |
| Qwen-VL 235BStrategy=VFD, Evaluation Status=Zero-shot2026.02 | 0.543 | |
| Gemini 3 ProStrategy=VTG, Evaluation Status=Zero-shot2026.02 | 0.54 | |
| GPT-5 MiniStrategy=VFD, Evaluation Status=Zero-shot2026.02 | 0.537 | |
| Claude Sonnet 4.5Strategy=CVPO, Evaluation Status=Zero-shot2026.02 | 0.536 | |
| Claude Sonnet 4.5Strategy=VTG, Evaluation Status=Zero-shot2026.02 | 0.535 | |
| GPT-4oStrategy=VFD, Evaluation Status=Zero-shot2026.02 | 0.535 | |
| Gemini 3 ProStrategy=CVPO, Evaluation Status=Zero-shot2026.02 | 0.533 | |
| Gemini 3 FlashStrategy=CVPO, Evaluation Status=Zero-shot2026.02 | 0.532 | |
| Claude Sonnet 4.5Strategy=VFD, Evaluation Status=Zero-shot2026.02 | 0.529 | |
| Llama 4 MaverickStrategy=VFD, Evaluation Status=Zero-shot2026.02 | 0.529 | |
| Gemini 3 ProStrategy=VFD, Evaluation Status=Zero-shot2026.02 | 0.5 | |
| Gemini 3 FlashStrategy=VFD, Evaluation Status=Zero-shot2026.02 | 0.497 | |
| GPT-5.2Strategy=VTG, Evaluation Status=Original2026.02 | 0.34 | |
| GPT-5.2Strategy=CVPO, Evaluation Status=Original2026.02 | 0.326 | |
| Claude Sonnet 4.5Strategy=VTG, Evaluation Status=Original2026.02 | 0.316 | |
| Llama 4 MaverickStrategy=VTG, Evaluation Status=Original2026.02 | 0.313 | |
| GPT-5.2Strategy=VFD, Evaluation Status=Original2026.02 | 0.31 | |
| Claude Haiku 4.5Strategy=VTG, Evaluation Status=Original2026.02 | 0.309 | |
| Claude Haiku 4.5Strategy=CVPO, Evaluation Status=Original2026.02 | 0.304 | |
| Claude Sonnet 4.5Strategy=CVPO, Evaluation Status=Original2026.02 | 0.304 | |
| Claude Sonnet 4.5Strategy=VFD, Evaluation Status=Original2026.02 | 0.303 | |
| GPT-5 MiniStrategy=VTG, Evaluation Status=Original2026.02 | 0.3 | |
| Gemini 3 FlashStrategy=VTG, Evaluation Status=Original2026.02 | 0.298 | |
| Claude Haiku 4.5Strategy=VFD, Evaluation Status=Original2026.02 | 0.292 | |
| Llama 4 MaverickStrategy=VFD, Evaluation Status=Original2026.02 | 0.292 | |
| Gemini 3 ProStrategy=VTG, Evaluation Status=Original2026.02 | 0.291 | |
| Llama 4 MaverickStrategy=CVPO, Evaluation Status=Original2026.02 | 0.29 | |
| Gemini 3 FlashStrategy=VFD, Evaluation Status=Original2026.02 | 0.287 | |
| GPT-5 MiniStrategy=CVPO, Evaluation Status=Original2026.02 | 0.284 | |
| GPT-5 MiniStrategy=VFD, Evaluation Status=Original2026.02 | 0.283 | |
| Gemini 3 ProStrategy=VFD, Evaluation Status=Original2026.02 | 0.274 | |
| Gemini 3 ProStrategy=CVPO, Evaluation Status=Original2026.02 | 0.273 | |
| GPT-4oStrategy=VTG, Evaluation Status=Original2026.02 | 0.271 | |
| Gemini 3 FlashStrategy=CVPO, Evaluation Status=Original2026.02 | 0.265 | |
| GPT-4oStrategy=VFD, Evaluation Status=Original2026.02 | 0.258 | |
| Qwen-VL 235BStrategy=VTG, Evaluation Status=Original2026.02 | 0.251 | |
| GPT-4oStrategy=CVPO, Evaluation Status=Original2026.02 | 0.246 | |
| Qwen-VL 235BStrategy=VFD, Evaluation Status=Original2026.02 | 0.233 | |
| Qwen-VL 235BStrategy=CVPO, Evaluation Status=Original2026.02 | 0.224 |