| mathematical-reasoning-on-mathverse | Co-RL (InternVL-3.5-8B, Different family) | #27 | Accuracy: 40.74 |
| multimodal-reasoning-on-mathvision | Co-RL (InternVL-3.5-8B, Different family) | #45 | Accuracy: 35.3 |
| multimodal-reasoning-on-mathvista | Co-RL (Qwen2.5-VL-7B, Different family) | #61 | Accuracy: 71.0 |
| code-generation-on-mbpp | Co-RL (Qwen2.5-7B, Different family) | #71 | Accuracy: 65.6 |
| code-generation-on-livecodebench-v6 | Co-RL (Qwen2.5-7B, Different family+) | #76 | Pass@1: 0.266 |
| code-generation-on-humaneval | Co-RL (Llama-3.1-8B-Instruct, Same family) | #86 | Pass@1: 68.3 |
| arithmetic-reasoning-on-gsm8k | Co-RL (Llama-3.1-8B-Instruct, Different family+) | #107 | Accuracy: 85.4 |
| mathematical-reasoning-on-math-500 | Co-RL (Qwen2.5-7B, Different family) | #109 | Accuracy: 75.2 |
| multiple-choice-question-answering-mcqa-on-gpqa-diamond | Co-RL (Qwen2.5-7B, Different family+) | #129 | Accuracy: 37.9 |