R3 Datasets R3 training datasets rubricreward/R3-Dataset-4K Viewer • Updated May 21 • 3.95k • 43 • 1 rubricreward/R3-Dataset-14K Viewer • Updated Jun 21 • 13.8k • 41 • 1 rubricreward/R3-Dataset-20K Viewer • Updated Jun 21 • 20k • 28 • 2
R3 Models Generate reward scores using generative models. rubricreward/R3-Qwen3-14B-LoRA-4k Text Generation • 15B • Updated May 21 • 27 • 2 rubricreward/R3-Qwen3-14B-4k Text Generation • 15B • Updated May 21 • 14 • 5 rubricreward/R3-Qwen3-14B-14k Text Generation • 15B • Updated May 21 • 11 • 2 rubricreward/R3-Qwen3-8B-LoRA-4k Text Generation • 8B • Updated May 21 • 12 • 1
R3 Benchmark Datasets R3 benchmark datasets rubricreward/R3-eval-RM-Bench Viewer • Updated May 15 • 11.9k • 37 rubricreward/R3-eval-reward-bench Viewer • Updated May 13 • 2.99k • 15 rubricreward/R3-eval-BBH Viewer • Updated 16 days ago • 13.5k • 115 rubricreward/R3-eval-MMLU-STEM Viewer • Updated 16 days ago • 6.31k • 133
R3 Models Generate reward scores using generative models. rubricreward/R3-Qwen3-14B-LoRA-4k Text Generation • 15B • Updated May 21 • 27 • 2 rubricreward/R3-Qwen3-14B-4k Text Generation • 15B • Updated May 21 • 14 • 5 rubricreward/R3-Qwen3-14B-14k Text Generation • 15B • Updated May 21 • 11 • 2 rubricreward/R3-Qwen3-8B-LoRA-4k Text Generation • 8B • Updated May 21 • 12 • 1
R3 Datasets R3 training datasets rubricreward/R3-Dataset-4K Viewer • Updated May 21 • 3.95k • 43 • 1 rubricreward/R3-Dataset-14K Viewer • Updated Jun 21 • 13.8k • 41 • 1 rubricreward/R3-Dataset-20K Viewer • Updated Jun 21 • 20k • 28 • 2
R3 Benchmark Datasets R3 benchmark datasets rubricreward/R3-eval-RM-Bench Viewer • Updated May 15 • 11.9k • 37 rubricreward/R3-eval-reward-bench Viewer • Updated May 13 • 2.99k • 15 rubricreward/R3-eval-BBH Viewer • Updated 16 days ago • 13.5k • 115 rubricreward/R3-eval-MMLU-STEM Viewer • Updated 16 days ago • 6.31k • 133
