Task 1 on BlenderBench
60.82PLQwen3-VL-8B
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Qwen3-VL-8BSetting=One-Shot2026.01 | 60.82 | 78.16 | 28 | — | |
| GPT-4oSetting=One-Shot2026.01 | 48.16 | 64.17 | 58 | — | |
| Gemini-2.5-ProSetting=One-Shot2026.01 | 40.65 | 49.57 | 175 | — | |
| Claude-Sonnet-4Setting=One-Shot2026.01 | 20.26 | 33.82 | 136 | — | |
| Gemini-2.5-ProSetting=VIGA2026.01 | 17.77 | 20.58 | 233 | 41.12 | |
| Qwen3-VL-8BSetting=VIGA2026.01 | 10.54 | 17.27 | 131 | 112.79 | |
| Claude-Sonnet-4Setting=VIGA2026.01 | 9.42 | 11.62 | 247 | 53.07 | |
| GPT-4oSetting=VIGA2026.01 | 8.56 | 18.19 | 144 | 113.96 |