Interactive View Planning on VIEWSUITE Interactive View Planning (Short)
33.7AccuracyGPT-5.4
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-5.4Model Category=Proprietary2026.05 | 33.7 | |
| GPT-5.4 ProModel Category=Proprietary2026.05 | 32.6 | |
| Gemini 3.1 ProModel Category=Proprietary2026.05 | 28.8 | |
| Claude Opus 4.6Model Category=Proprietary2026.05 | 23.9 | |
| Grok 4.20 BetaModel Category=Proprietary2026.05 | 17.4 | |
| Gemini 3 ProModel Category=Proprietary2026.05 | 13.6 | |
| Qwen3.5-397BModel Category=Open-Weight2026.05 | 12.5 | |
| GPT-5.1Model Category=Proprietary2026.05 | 12 | |
| GLM-4.6VModel Category=Open-Weight2026.05 | 9.2 | |
| Qwen2.5-VL-7BModel Category=Open-Weight2026.05 | 7.1 | |
| Kimi K2.5Model Category=Open-Weight2026.05 | 4.9 | |
| Qwen3-VL-32BModel Category=Open-Weight2026.05 | 4.3 | |
| Random ResponseModel Category=Baseline2026.05 | 2.2 | |
| Qwen2.5-VL-72BModel Category=Open-Weight2026.05 | 2.2 |