Question Answering on SimpleQA Sim (Accuracy)
8AccuracyKDoS
Evaluation Results
| Method | Links | |
|---|---|---|
| KDoSBackbone=Qwen3-4B-Base2026.06 | 8 | |
| Diff.Backbone=Qwen3-4B-Base, Synthesis Strategy=Difficulty-weighted2026.06 | 7.2 | |
| Uni.Backbone=Qwen3-4B-Base, Synthesis Strategy=Uniform2026.06 | 6.6 | |
| Qual.Backbone=Qwen3-4B-Base, Synthesis Strategy=Quality-filtered2026.06 | 6.3 | |
| Rand.Backbone=Qwen3-4B-Base, Synthesis Strategy=Random2026.06 | 6 | |
| SPBackbone=Qwen3-4B-Base, Training Data=Seed Pool2026.06 | 5.8 | |
| BaseBackbone=Qwen3-4B-Base2026.06 | 3.5 |