Composition-RL: Compose Your Verifiable Prompts for Reinforcement Learning of Large Language Models
Open paper
Benchmark
Model
Rank
Results
mathematical-reasoning-on-aime24
Qwen3-14B-Base + Composition-RL (12K subset)
#91
Acc: 43.3
multiple-choice-question-answering-mcqa-on-gpqa-diamond
Qwen3-14B-Base + Composition-RL (12K subset)
#106
Accuracy: 54.7
Rank counts only results with a code link.