List your company

Mathematical Reasoning on GSM8K (Accuracy, Avg Acc, Avg TPF)

94.31AccuracyQwen3-14B
60.801269.500678.286.8994Jul 7, 2026

Evaluation results

MethodLinks
Qwen3-14BScale=14B, Gen. Mode=AR2026.0794.3165.171
Nemotron-Labs-Diffusion-14BScale=14B, Gen. Mode=Diff.2026.0793.7166.512.74
Ministral3-14B-Instruct-2512Scale=14B, Gen. Mode=AR2026.0792.862.971
Phi-4-14BScale=14B, Gen. Mode=AR2026.0792.2760.821
Qwen3-4BScale=3B, Gen. Mode=AR2026.0792.1953.231
Nemotron-Labs-Diffusion-14BScale=14B, Gen. Mode=Quad. SS2026.0792.1268.156.92
Nemotron-Labs-Diffusion-14BScale=14B, Gen. Mode=Linear SS2026.0792.0466.365.96
Nemotron-Labs-Diffusion-14BScale=14B, Gen. Mode=AR2026.0791.3667.461
Gemma-3-12B-ITScale=14B, Gen. Mode=AR2026.0790.4558.031
Phi-3-Medium-14BScale=14B, Gen. Mode=AR2026.0789.6949.341
Nemotron-Labs-Diffusion-3BScale=3B, Gen. Mode=Diff.2026.0788.452.91.91
Nemotron-Labs-Diffusion-3BScale=3B, Gen. Mode=Quad. SS2026.0788.2555.85.42
Nemotron-Labs-Diffusion-3BScale=3B, Gen. Mode=AR2026.0787.8755.51
Nemotron-Labs-Diffusion-3BScale=3B, Gen. Mode=Linear SS2026.0787.79554.36
Ministral3-3B-Instruct-2512Scale=3B, Gen. Mode=AR2026.0787.4147.971
Phi-4-mini-InstructScale=3B, Gen. Mode=AR2026.0776.5749.21
Llama-3.2-3B-InstructScale=3B, Gen. Mode=AR2026.0762.0939.91