| A natural way to evaluate code programs is to see if they pass unit tests, it is the idea behind the [pass@k](https://huggingface.co/metrics/code_eval) metric, a popular evaluation framework for code generation models, on [HumanEval](https://huggingface.co/datasets/openai_humaneval) dataset, which was introduced in [Codex paper](https://arxiv.org/pdf/2107.03374v2.pdf). The dataset includes 164 handwritten programming problems. In the pass@k metric, k code samples are generated per problem, and a problem is considered solved if any sample passes the unit tests and the total fraction of problems solved is reported. | |
| In most papers, 200 candidate program completions are sampled, and pass@1, pass@10, and pass@100 are computed using an unbiased sampling estimator. Table 1 below shows the HumanEval scores of CodeParrot, InCoder, PolyCoder, CodeGen and Codex (not open-source). | |
| <div align="center"> | |
| Model | pass@1 | pass@10 | pass@100| | |
| |-------|--------|---------|---------| | |
| |CodeParrot (110M) | 3.80% | 6.57% | 12.78% | | |
| |CodeParrot (1.5B) | 3.58% | 8.03% | 14.96% | | |
| ||||| | |
| |InCoder (6.7B) | 15.2% | 27.8% | 47.00% | | |
| ||||| | |
| |PolyCoder (160M)| 2.13% | 3.35% | 4.88% | | |
| |PolyCoder (400M)| 2.96% | 5.29% | 11.59% | | |
| |PolyCoder (2.7B)| 5.59% | 9.84% | 17.68% | | |
| ||||| | |
| |CodeGen-Mono (350M)| 12.76% | 23.11% | 35.19% | | |
| |CodeGen-Mono (2.7B)| 23.70% | 36.64% | 57.01% | | |
| |CodeGen-Mono (6.1B)| 26.13% | 42.29% | 65.82% | | |
| |CodeGen-Mono (16.1B)| **29.28%** | **49.86%** | **75.00%** | | |
| ||||| | |
| |Codex (25M)| 3.21% | 7.1% | 12.89%| | |
| |Codex (300M)| 13.17%| 20.37% | 36.27% | | |
| |Codex (12B)| 28.81%| 46.81% | 72.31% | | |
| </div> |