List your company

Code Generation on HumanEval (Accuracy, Avg.)

81.71AccuracyQwen3 8B
33.516446.028258.5471.0518May 25, 2026Jun 1, 2026Jun 8, 2026Jun 15, 2026Jun 22, 2026Jun 29, 2026Jul 7, 2026

Evaluation results

MethodLinks
Qwen3 8BGen. Mode=AR, TPF=1.002026.0781.71—
Nemotron-Labs-Diffusion-8BGen. Mode=Linear SS, TPF=5.992026.0781.71—
Nemotron-Labs-Diffusion-8BGen. Mode=AR, TPF=1.002026.0780.49—
SDAR-8B ChatGen. Mode=Diff., TPF=1.752026.0779.27—
Nemotron-Labs-Diffusion-8BGen. Mode=Quad. SS, TPF=6.382026.0779.27—
SDAR-8B ChatGen. Mode=Diff., TPF=1.002026.0778.7—
Nemotron-Labs-Diffusion-8BGen. Mode=Diff., TPF=2.572026.0778.66—
Qwen2.5 7BGen. Mode=AR, TPF=1.002026.0777.44—
Ministral3-8B Instruct-2512Gen. Mode=AR, TPF=1.002026.0771.04—
Dream-7B InstructGen. Mode=Diff., TPF=1.002026.0755.5—
LLaDA-8B InstructGen. Mode=Diff., TPF=1.002026.0749.4—
Skew F(R)KLTeacher-Student=DeepSeek-Coder-6.7B -> 1.3B2026.0542.0747.29
α-β divergenceTeacher-Student=DeepSeek-Coder-6.7B -> 1.3B2026.0541.4647.09
HybKDTeacher-Student=DeepSeek-Coder-6.7B -> 1.3B2026.0541.4647.89
Reverse KLTeacher-Student=DeepSeek-Coder-6.7B -> 1.3B2026.0539.0246.34
Forward KLTeacher-Student=DeepSeek-Coder-6.7B -> 1.3B2026.0538.4146.76
Hard KDTeacher-Student=DeepSeek-Coder-6.7B -> 1.3B2026.0535.3744.66