Scientific Reasoning on Scientific Reasoning Tasks Agentic Subset
56.79Avg@8Agentic Self-Instruct
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Agentic Self-InstructTraining Data Source=Agentic Self-Instruct, Base Model=Qwen3.5-4B2026.06 | 56.79 | 81.86 | 4.4 | |
| CoT Self-InstructTraining Data Source=CoT Self-Instruct, Base Model=Qwen3.5-4B2026.06 | 56.33 | 81.74 | 3.94 | |
| Combined (2× data)Training Data Source=Combined, Training Data Size=2× data, Base Model=Qwen3.5-4B2026.06 | 55.88 | 82.11 | 3.49 | |
| Qwen3.5-4BTraining Data Source=Base, Base Model=Qwen3.5-4B2026.06 | 52.39 | 81.13 | — |