List your company

Grade School Math Reasoning on GSM8k (test)

94.84AccuracyJF-HPO
66.219273.649681.0888.5104Jun 2, 2026

Evaluation results

MethodLinks
JF-HPOModel=Qwen-3 14B2026.0694.84
VeRL RecipeModel=Qwen-3 14B2026.0693.03
JF-HPOModel=Qwen-2.5 7B2026.0688.17
JF-HPOModel=LLaMA-3.1 8B2026.0687.11
BOHBModel=LLaMA-3.1 8B2026.0686.66
Random SearchModel=Qwen-2.5 7B2026.0684.99
VeRL RecipeModel=Qwen-2.5 7B2026.0683.47
BOHBModel=Qwen-2.5 7B2026.0681.65
Random SearchModel=LLaMA-3.1 8B2026.0678.39
VeRL RecipeModel=LLaMA-3.1 8B2026.0667.32