List your company

Scientific Reasoning on Scientific Reasoning Tasks Starting Qwen3.5-4B model (Overall)

71.86Average Score @8Agentic Self-Instruct
68.53269.39670.2671.124Jun 24, 2026

Evaluation results

MethodLinks
Agentic Self-InstructTraining Data Source=Agentic Self-Instruct, Base Model=Qwen3.5-4B2026.0671.8688.913.2
Combined (2× data)Training Data Source=Combined, Training Data Size=2× data, Base Model=Qwen3.5-4B2026.0671.3688.752.7
CoT Self-InstructTraining Data Source=CoT Self-Instruct, Base Model=Qwen3.5-4B2026.0671.0888.582.42
Qwen3.5-4BTraining Data Source=Base, Base Model=Qwen3.5-4B2026.0668.6687.73—