# Code Generation on MBPP subset of 500 (test)

Source: [Code Generation on MBPP subset of 500 (test)](<https://www.sota2.com/research/sota/code-generation-on-mbpp-subset-of-500-test>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:57:21.016Z

Evaluation of model performance on the specific test subset of 500 problems from the Mostly Basic Python Programming (MBPP) dataset for code generation tasks, typically measured using Pass@1.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Code Generation |
| Dataset (including any stated split) | MBPP subset of 500 (test) |
| Metric | Pass@1 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 18 of 18 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Pass@1](<https://www.sota2.com/research/sota/code-generation-on-mbpp-subset-of-500-test.md?metric=Pass%401>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Pass@1 | Result date | Report paper |
| --- | --- | --- | --- |
| Magicoder-S-DS | 64.6 | Not recorded | 68fa738f1e209131cea5d375 |
| WaveCoder-Ultra-6.7B | 64.4 | Not recorded | 68fa738f1e209131cea5d375 |
| WaveCoder-Pro-6.7B | 63.6 | Not recorded | 68fa738f1e209131cea5d375 |
| WaveCoder-DS-6.7B | 62.8 | Not recorded | 68fa738f1e209131cea5d375 |
| DeepseekCoder-instruct\* | 62.8 | Not recorded | 68fa738f1e209131cea5d375 |
| DeepseekCoder | 60.6 | Not recorded | 68fa738f1e209131cea5d375 |
| Magicoder-DS | 60.4 | Not recorded | 68fa738f1e209131cea5d375 |
| ChatGPT | 52.2 | Not recorded | 68fa738f1e209131cea5d375 |
| WizardCoder | 51.8 | Not recorded | 68fa738f1e209131cea5d375 |
| WaveCoder-SC-15B | 51 | Not recorded | 68fa738f1e209131cea5d375 |
| WaveCoder-CL-13B | 49.6 | Not recorded | 68fa738f1e209131cea5d375 |
| CodeLLaMa-instruct | 49.4 | Not recorded | 68fa738f1e209131cea5d375 |
| WaveCoder-CL-7B | 47.2 | Not recorded | 68fa738f1e209131cea5d375 |
| CodeLLaMa | 47 | Not recorded | 68fa738f1e209131cea5d375 |
| CodeLLaMa-instruct | 44.4 | Not recorded | 68fa738f1e209131cea5d375 |
| OctoCoder | 43.5 | Not recorded | 68fa738f1e209131cea5d375 |
| StarCoder | 43.3 | Not recorded | 68fa738f1e209131cea5d375 |
| CodeLLaMa | 41.4 | Not recorded | 68fa738f1e209131cea5d375 |

### Magicoder-S-DS

Pass@1: 64.6. Result ID: 699300283a6c31484912f5df.

[Reporting paper](<https://www.sota2.com/research/paper/68fa738f1e209131cea5d375.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa738f1e209131cea5d36a.md>)

Recorded evaluation configuration: {"Params":"6.7B","Base Model":"DeepseekCoder","InsT Data":"185K","Decoding Strategy":"greedy"}. This record does not assert independent reproduction.

### WaveCoder-Ultra-6.7B

Pass@1: 64.4. Result ID: 699300283a6c31484912f5e0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa738f1e209131cea5d375.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa738f1e209131cea5d375.md>)

Recorded evaluation configuration: {"Params":"6.7B","Base Model":"DeepseekCoder","InsT Data":"130K","Decoding Strategy":"greedy"}. This record does not assert independent reproduction.

### WaveCoder-Pro-6.7B

Pass@1: 63.6. Result ID: 699300283a6c31484912f5dd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa738f1e209131cea5d375.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa738f1e209131cea5d375.md>)

Recorded evaluation configuration: {"Params":"6.7B","Base Model":"DeepseekCoder","InsT Data":"20K","Decoding Strategy":"greedy"}. This record does not assert independent reproduction.

### WaveCoder-DS-6.7B

Pass@1: 62.8. Result ID: 699300283a6c31484912f5dc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa738f1e209131cea5d375.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa738f1e209131cea5d375.md>)

Recorded evaluation configuration: {"Params":"6.7B","Base Model":"DeepseekCoder","InsT Data":"20K","Decoding Strategy":"greedy"}. This record does not assert independent reproduction.

### DeepseekCoder-instruct\*

Pass@1: 62.8. Result ID: 699300283a6c31484912f5de.

[Reporting paper](<https://www.sota2.com/research/paper/68fa738f1e209131cea5d375.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa738f1e209131cea5d36a.md>)

Recorded evaluation configuration: {"Params":"6.7B","Base Model":"DeepseekCoder","Decoding Strategy":"greedy"}. This record does not assert independent reproduction.

### DeepseekCoder

Pass@1: 60.6. Result ID: 699300283a6c31484912f5da.

[Reporting paper](<https://www.sota2.com/research/paper/68fa738f1e209131cea5d375.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71f21e209131cea53b4b.md>)

[Implementation](<https://github.com/deepseek-ai/DeepSeek-Coder>)

Recorded evaluation configuration: {"Params":"6.7B","InsT Data":"None","Decoding Strategy":"greedy"}. This record does not assert independent reproduction.

### Magicoder-DS

Pass@1: 60.4. Result ID: 699300283a6c31484912f5db.

[Reporting paper](<https://www.sota2.com/research/paper/68fa738f1e209131cea5d375.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa738f1e209131cea5d36a.md>)

Recorded evaluation configuration: {"Params":"6.7B","Base Model":"DeepseekCoder","InsT Data":"75K","Decoding Strategy":"greedy"}. This record does not assert independent reproduction.

### ChatGPT

Pass@1: 52.2. Result ID: 699300283a6c31484912f5cf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa738f1e209131cea5d375.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa727a1e209131cea56a1e.md>)

[Implementation](<https://github.com/openai/evals>)

Recorded evaluation configuration: {"Decoding Strategy":"n=200"}. This record does not assert independent reproduction.

### WizardCoder

Pass@1: 51.8. Result ID: 699300283a6c31484912f5d2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa738f1e209131cea5d375.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78da1e209131cea7ad08.md>)

[Implementation](<https://github.com/nlpxucan/WizardLM>)

Recorded evaluation configuration: {"Params":"15B","Base Model":"StarCoder","InsT Data":"78K","Decoding Strategy":"n=200"}. This record does not assert independent reproduction.

### WaveCoder-SC-15B

Pass@1: 51. Result ID: 699300283a6c31484912f5d3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa738f1e209131cea5d375.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa738f1e209131cea5d375.md>)

Recorded evaluation configuration: {"Params":"15B","Base Model":"StarCoder","InsT Data":"20K","Decoding Strategy":"n=200"}. This record does not assert independent reproduction.

### WaveCoder-CL-13B

Pass@1: 49.6. Result ID: 699300283a6c31484912f5d9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa738f1e209131cea5d375.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa738f1e209131cea5d375.md>)

Recorded evaluation configuration: {"Params":"13B","Base Model":"CodeLLaMa","InsT Data":"20K","Decoding Strategy":"n=200"}. This record does not assert independent reproduction.

### CodeLLaMa-instruct

Pass@1: 49.4. Result ID: 699300283a6c31484912f5d8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa738f1e209131cea5d375.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71ff1e209131cea53ff7.md>)

[Implementation](<https://github.com/facebookresearch/codellama>)

Recorded evaluation configuration: {"Params":"13B","Base Model":"CodeLLaMa","InsT Data":"14K","Decoding Strategy":"n=200"}. This record does not assert independent reproduction.

### WaveCoder-CL-7B

Pass@1: 47.2. Result ID: 699300283a6c31484912f5d6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa738f1e209131cea5d375.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa738f1e209131cea5d375.md>)

Recorded evaluation configuration: {"Params":"7B","Base Model":"CodeLLaMa","InsT Data":"20K","Decoding Strategy":"n=200"}. This record does not assert independent reproduction.

### CodeLLaMa

Pass@1: 47. Result ID: 699300283a6c31484912f5d7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa738f1e209131cea5d375.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71ff1e209131cea53ff7.md>)

[Implementation](<https://github.com/facebookresearch/codellama>)

Recorded evaluation configuration: {"Params":"13B","InsT Data":"None","Decoding Strategy":"n=200"}. This record does not assert independent reproduction.

### CodeLLaMa-instruct

Pass@1: 44.4. Result ID: 699300283a6c31484912f5d5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa738f1e209131cea5d375.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71ff1e209131cea53ff7.md>)

[Implementation](<https://github.com/facebookresearch/codellama>)

Recorded evaluation configuration: {"Params":"7B","Base Model":"CodeLLaMa","InsT Data":"14K","Decoding Strategy":"n=200"}. This record does not assert independent reproduction.

### OctoCoder

Pass@1: 43.5. Result ID: 699300283a6c31484912f5d1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa738f1e209131cea5d375.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72381e209131cea5507f.md>)

Recorded evaluation configuration: {"Params":"15B","Base Model":"StarCoder","InsT Data":"13K","Decoding Strategy":"n=200"}. This record does not assert independent reproduction.

### StarCoder

Pass@1: 43.3. Result ID: 699300283a6c31484912f5d0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa738f1e209131cea5d375.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa717d1e209131cea5197b.md>)

Recorded evaluation configuration: {"Params":"15B","InsT Data":"None","Decoding Strategy":"n=200"}. This record does not assert independent reproduction.

### CodeLLaMa

Pass@1: 41.4. Result ID: 699300283a6c31484912f5d4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa738f1e209131cea5d375.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71ff1e209131cea53ff7.md>)

[Implementation](<https://github.com/facebookresearch/codellama>)

Recorded evaluation configuration: {"Params":"7B","InsT Data":"None","Decoding Strategy":"n=200"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
