Ours 4B (Grounded-CoT)
| Method | Links | ||||
|---|---|---|---|---|---|
2026.03 | 70 | 71.5 | 66.33 | 74.75 | |
2026.03 | 60.76 | 47.5 | 62.33 | 67.6 | |
2026.03 | 59.92 | 49 | 56.5 | 70.5 | |
2026.03 | 55.24 | 49.5 | 52.5 | 66.4 | |
2026.03 | 47.62 | 37 | 50.38 | 26.91 | |
2026.03 | 46.67 | 38.39 | 48.38 | 34.63 | |
2026.03 | 46.64 | 89 | 44.67 | 51.75 | |
2026.03 | 44.75 | 48.42 | 44.21 | 47.62 | |
2026.03 | 41.05 | 37.65 | 40.23 | 50.99 | |
2026.03 | 40.08 | 24.5 | 45.5 | 39.75 | |
2026.03 | 38.81 | 32.65 | 40.17 | 29.16 | |
2026.03 | 38.58 | 44 | 38.67 | 35.75 | |
2026.03 | 37.42 | 46 | 35.83 | 35.5 | |
2026.03 | 37.38 | 35.8 | 38.28 | 29.53 | |
2026.03 | 37.33 | 36 | 38.83 | 35.75 | |
2026.03 | 36.67 | 41.5 | 34.67 | 37.25 | |
2026.03 | 35.86 | 35.15 | 35.94 | 35.49 | |
2026.03 | 34.33 | 27.5 | 36.5 | 34.5 | |
2026.03 | 33.02 | 38.3 | 32.66 | 35.79 | |
2026.03 | 32.58 | 26.5 | 36.33 | 30 | |
2026.03 | 32.35 | 36.36 | 32.29 | 30.66 | |
2026.03 | 32.06 | 38.39 | 20.92 | 32.82 | |
2026.03 | 29.26 | 38.76 | 29.5 | 21.35 | |
2026.03 | 18.68 | 36.45 | 47.11 | 26.91 |