Mathematical Reasoning on MATH500 (Pass@16)
91.4Pass@16Qwen2.5-7B + GRPO w/ VERL.
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen2.5-7B + GRPO w/ VERL.Base Model=Qwen2.5-7B, RL Framework=GRPO, VERL Integration=true, Decoding Setting=Pass@162025.09 | 91.4 | |
| Qwen2.5-7B + PPO w/ VERL.Base Model=Qwen2.5-7B, RL Framework=PPO, VERL Integration=true, Decoding Setting=Pass@162025.09 | 91.4 | |
| Qwen2.5-7B + PPOBase Model=Qwen2.5-7B, RL Framework=PPO, Decoding Setting=Pass@162025.09 | 91.2 | |
| Qwen2.5-7B + GRPOBase Model=Qwen2.5-7B, RL Framework=GRPO, Decoding Setting=Pass@162025.09 | 90.8 | |
| Qwen2.5-7BBase Model=Qwen2.5-7B, RL Framework=None, Decoding Setting=Pass@162025.09 | 90.6 | |
| Llama-3.2-3B-Instruct + PPO w/ VERL.Base Model=Llama-3.2-3B-Instruct, RL Framework=PPO, VERL Integration=true, Decoding Setting=Pass@162025.09 | 82.4 | |
| Llama-3.2-3B-Instruct + PPOBase Model=Llama-3.2-3B-Instruct, RL Framework=PPO, Decoding Setting=Pass@162025.09 | 82.2 | |
| Llama-3.2-3B-Instruct + GRPO w/ VERL.Base Model=Llama-3.2-3B-Instruct, RL Framework=GRPO, VERL Integration=true, Decoding Setting=Pass@162025.09 | 80.6 | |
| Llama-3.2-3B-Instruct + GRPOBase Model=Llama-3.2-3B-Instruct, RL Framework=GRPO, Decoding Setting=Pass@162025.09 | 80.2 | |
| Llama-3.2-3B-InstructBase Model=Llama-3.2-3B-Instruct, RL Framework=None, Decoding Setting=Pass@162025.09 | 79.8 |