| Benchmark | Model | Rank | Results |
|---|---|---|---|
| code-generation-on-mbpp | ReFusion | #63 | Accuracy: 68.2 |
| code-generation-on-humaneval | ReFusion | #67 | Pass@1: 78.66 |
| math-word-problem-solving-on-math | ReFusion | #70 | Accuracy: 54.22 |
| arithmetic-reasoning-on-gsm8k | ReFusion | #111 | Accuracy: 84.91 |
| multi-task-language-understanding-on-mmlu-pro | ReFusion | #121 | Accuracy: 45.94 |