Ancient Chinese character evolution reasoning on OBIsEvolution OOD
69.55T1.1 ScoreGEVO
Evaluation Results
| Method | Links | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| GEVO2026.04 | 69.55 | 81.95 | 79.8 | 56.84 | 87.84 | 92.57 | 90.54 | 79.75 | 97.3 | 81.79 | |
| Qwen3-VL-8B-InstructModel Scale=8B2026.04 | 45.53 | 70.55 | 61.2 | 47.63 | 75.34 | 65.54 | 71.62 | 45.62 | 74.32 | 61.93 | |
| Qwen3-VL-2B-InstructModel Scale=2B2026.04 | 24.3 | 59.05 | 28.5 | 41.34 | 69.59 | 25 | 70.27 | 23.09 | 46.62 | 43.08 |