General Performance on General Evaluation Suite
73.8AccuracyQwen3 8B
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen3 8B2026.02 | 73.8 | |
| Full KDDistillation Regime=Off-policy2026.02 | 64.5 | |
| RandomPos 20%Distillation Regime=Off-policy, Selection Budget=20%2026.02 | 64 | |
| SE-KD + TopSmp 20%Distillation Regime=Off-policy, Selection Budget=20%2026.02 | 64 | |
| SE-KDDistillation Regime=Off-policy2026.02 | 63.9 | |
| SE-KD3XDistillation Regime=Off-policy2026.02 | 63.9 | |
| Full KDDistillation Regime=On-policy2026.02 | 63.7 | |
| SE-KDDistillation Regime=On-policy2026.02 | 63.7 | |
| TopSmp 20%Distillation Regime=On-policy, Selection Budget=20%2026.02 | 63.7 | |
| TopSmp 20%Distillation Regime=Off-policy, Selection Budget=20%2026.02 | 63.6 | |
| Pos RS-KD 20%Distillation Regime=Off-policy, Selection Budget=20%2026.02 | 63.5 | |
| SE-KD + TopSmp 20%Distillation Regime=On-policy, Selection Budget=20%2026.02 | 63.4 | |
| Pos RS-KD* 20%Distillation Regime=Off-policy, Selection Budget=20%2026.02 | 63.3 | |
| RandomPos 20%Distillation Regime=On-policy, Selection Budget=20%2026.02 | 63.3 | |
| Pos RS-KD* 20%Distillation Regime=On-policy, Selection Budget=20%2026.02 | 63.3 | |
| Pos RS-KD 20%Distillation Regime=On-policy, Selection Budget=20%2026.02 | 63.2 | |
| Qwen3 1.7B2026.02 | 61.9 |