List your company

Diversity Evaluation on Open-ended Random Generation

864.5Top-90% Support SizeQwen3-1.7B
-32.188200.606433.4666.194May 12, 2026

Evaluation results

MethodLinks
Qwen3-1.7BCalibration=Soft2026.05864.539.1
Qwen3-0.6BCalibration=Soft2026.05711.245.3
Qwen3-14BCalibration=Soft2026.05536.249.1
Qwen3-0.6BCalibration=Hard2026.05501.645.9
Qwen3-8BCalibration=Soft2026.05466.937.9
Qwen3-4BCalibration=Soft2026.05299.627.7
GPT-OSS-20BCalibration=Soft2026.0528973
Qwen3-1.7BCalibration=Hard2026.0526530.3
Qwen3-8BCalibration=Hard2026.05219.627.8
GPT-OSS-20BCalibration=Hard2026.05212.477.1
Qwen3-14BCalibration=Hard2026.0519435.9
Qwen3-4BCalibration=Hard2026.05127.821.4
Gemma-3-4B-itCalibration=Soft2026.0511549.2
Llama-3.2-1B-itCalibration=Soft2026.0586.217.7
Llama-3.2-3B-itCalibration=Soft2026.0585.618.8
Llama-3.2-1B-itCalibration=Base2026.0584.652.5
Llama-3.2-1B-itCalibration=Hard2026.0583.918.4
Llama-3.2-3B-itCalibration=Hard2026.0578.917.9
Gemma-3-27B-itCalibration=Soft2026.056340.1
Gemma-3-1B-itCalibration=Soft2026.0552.616.8
Qwen3-0.6BCalibration=Base2026.054556.9
Gemma-3-12B-itCalibration=Soft2026.0544.831.8
Gemma-3-27B-itCalibration=Hard2026.0539.430
Gemma-3-1B-itCalibration=Hard2026.0536.617.3
Llama-3.2-3B-itCalibration=Base2026.0528.936.4
GPT-OSS-20BCalibration=Base2026.052836.2
Gemma-3-12B-itCalibration=Hard2026.0523.621.4
Gemma-3-4B-itCalibration=Hard2026.0522.925
Qwen3-1.7BCalibration=Base2026.058.822.5
Gemma-3-1B-itCalibration=Base2026.055.513.3
Qwen3-4BCalibration=Base2026.054.411.9
Qwen3-14BCalibration=Base2026.053.510.9
Qwen3-8BCalibration=Base2026.053.39.5
Gemma-3-12B-itCalibration=Base2026.053.37.4
Gemma-3-4B-itCalibration=Base2026.052.66.9
Gemma-3-27B-itCalibration=Base2026.052.35.8