Interactive View Planning on VIEWSUITE Interactive View Planning (All)
21.4AccuracyGemini 3.1 Pro
Evaluation results
| Method | Links | |
|---|---|---|
| Gemini 3.1 ProModel Category=Proprietary2026.05 | 21.4 | |
| GPT-5.4 ProModel Category=Proprietary2026.05 | 18.5 | |
| GPT-5.4Model Category=Proprietary2026.05 | 16.6 | |
| Claude Opus 4.6Model Category=Proprietary2026.05 | 10.8 | |
| Gemini 3 ProModel Category=Proprietary2026.05 | 9.3 | |
| Grok 4.20 BetaModel Category=Proprietary2026.05 | 7.9 | |
| GPT-5.1Model Category=Proprietary2026.05 | 6.2 | |
| Qwen3.5-397BModel Category=Open-Weight2026.05 | 4.3 | |
| GLM-4.6VModel Category=Open-Weight2026.05 | 4 | |
| Kimi K2.5Model Category=Open-Weight2026.05 | 2.5 | |
| Qwen2.5-VL-7BModel Category=Open-Weight2026.05 | 2.5 | |
| Qwen3-VL-32BModel Category=Open-Weight2026.05 | 1.5 | |
| Qwen2.5-VL-72BModel Category=Open-Weight2026.05 | 1.1 | |
| Random ResponseModel Category=Baseline2026.05 | 0.8 |