Planning on LLM-BabyBench Planning
89.33AccuracyVeryTrace
Evaluation Results
| Method | Links | |
|---|---|---|
| VeryTraceModel=Q3-80b-T2026.06 | 89.33 | |
| VeryTraceModel=Q3-80b-I2026.06 | 78 | |
| CoVeModel=Q3-80b-T2026.06 | 70 | |
| NPModel=Q3-80b-T2026.06 | 68.33 | |
| VanillaModel=Q3-80b-T2026.06 | 60.33 | |
| CoVeModel=Q3-80b-I2026.06 | 50 | |
| NPModel=Q3-80b-I2026.06 | 45 | |
| VanillaModel=Q3-80b-I2026.06 | 40 | |
| VeryTraceModel=L3.3-70b-I2026.06 | 36.33 | |
| CoVeModel=L3.3-70b-I2026.06 | 13.67 | |
| NPModel=L3.3-70b-I2026.06 | 11 | |
| VanillaModel=L3.3-70b-I2026.06 | 8.67 |