List your company

STEM Knowledge and Reasoning on GPQA Diamond MMLU Reduced

58.86GPQA Diamond AccuracyTeacher
23.905632.980342.05551.1297May 31, 2026

Evaluation results

MethodLinks
TeacherDistillation Setting=Multi-Domain Distillation, Teacher Model=Qwen3-Nemotron-4B2026.0558.8677.03
TrOPDDistillation Setting=Multi-Domain Distillation, Student Model=Qwen3-SFT-1.7B, Teacher Model=Qwen3-Nemotron-4B2026.0535.9868.74
EOPDDistillation Setting=Multi-Domain Distillation, Student Model=Qwen3-SFT-1.7B, Teacher Model=Qwen3-Nemotron-4B2026.0533.8468.26
REOPOLDDistillation Setting=Multi-Domain Distillation, Student Model=Qwen3-SFT-1.7B, Teacher Model=Qwen3-Nemotron-4B2026.0530.5668.3
Entropy OPDDistillation Setting=Multi-Domain Distillation, Student Model=Qwen3-SFT-1.7B, Teacher Model=Qwen3-Nemotron-4B2026.0529.9268.51
OPDDistillation Setting=Multi-Domain Distillation, Student Model=Qwen3-SFT-1.7B, Teacher Model=Qwen3-Nemotron-4B2026.0529.868.6
Qwen3-SFT-1.7BDistillation Setting=Baseline (None), Student Model=Qwen3-SFT-1.7B2026.0525.2566.6