Code Generation on Code2World
96.51S_adMobileWorldModel-8B
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| MobileWorldModel-8BParameters=8B2026.05 | 96.51 | 94.6 | 79.14 | 81.43 | 87.11 | 73.87 | 85.44 | |
| Code2World-8BParameters=8B2026.05 | 94.28 | 88.64 | 71.35 | 70.32 | 79.44 | 49.18 | 75.53 | |
| GPT-52026.05 | 94.02 | 90.15 | 74.13 | 69.78 | 78.07 | 41.74 | 74.64 | |
| Gemini-3-Flash2026.05 | 92.65 | 84.08 | 74.52 | 69.74 | 81.17 | 45.72 | 74.65 | |
| GLM-4.6V-106BParameters=106B2026.05 | 91.62 | 74.23 | 61.95 | 58.74 | 67.26 | 27.42 | 63.53 | |
| Claude-4.5-Sonnet2026.05 | 89.6 | 86.12 | 65.8 | 62.25 | 75.97 | 36.72 | 69.41 | |
| Qwen2.5-VL-72BParameters=72B2026.05 | 73.34 | 70.12 | 47.15 | 48.26 | 68.45 | 30.12 | 56.24 | |
| InternVL3-78BParameters=78B2026.05 | 72.41 | 67.35 | 45.06 | 46.73 | 62.64 | 25.42 | 53.26 | |
| Qwen3-VL-8BParameters=8B2026.05 | 59.2 | 65.8 | 43.1 | 42.7 | 63.88 | 28.86 | 50.59 | |
| JanusCoderV-7BParameters=7B2026.05 | 57.12 | 56.05 | 30.18 | 31.09 | 59.89 | 21.73 | 42.68 |