Share your thoughts, 1 month free Claude Pro on usSee more

Mathematical Reasoning on Math (FULL, CONCAT, RAW-SHARDED)

96.1Accuracy (FULL Mode)

Qwen3-14B Base

Updated 5d ago

Evaluation Results

Method	Links
Qwen3-14B Base 2026.05		96.1	92.9	71.8
Qwen3-8B Forward-CCOPD 2026.05		93.2	91.3	79
Qwen3-8B SFT 2026.05		93.2	91.3	66
Qwen3-8B 14B-teacher CCOPD 2026.05		92.2	86.4	69.9
Qwen3-8B GRPO 2026.05		91.3	90.3	74.8
Qwen3-8B 4B-teacher CCOPD 2026.05		90.3	88.4	68
Qwen3-8B Base 2026.05		90.3	87.4	66
Qwen3-8B CCOPD 2026.05		90.3	88.4	82.5
Qwen3-4B Base 2026.05		89.3	84.5	55.3
Qwen3-4B CCOPD 2026.05		89.3	83.5	56.9
Qwen3-8B OPSD 2026.05		86	85	56.3
Llama3.1-8B CCOPD 2026.05		74.8	73.8	53.4
Llama3.1-8B Base 2026.05		71.8	70.9	46.6