1. BigCodeBench-Complete: Code Completion based on the structured docstrings. 1. BigCodeBench-Instruct: Code Generation based on the NL-oriented instructions.
Rows5,700
Configurations1
Size16.6 MB
Licenseapache-2.0
AccessPublicly accessible
Monthly Downloads112.2k
Dataset Card
By BigCode, published under apache-2.0, revision b74c0d0bf70d.
Dataset Description
- Homepage: https://bigcode-bench.github.io/
- Repository: https://github.com/bigcode-project/bigcodebench
- Paper: Link
- Point of Contact: [email protected] [email protected]
The dataset has 2 variants:
1. BigCodeBench-Complete: Code Completion based on the structured docstrings.
1. BigCodeBench-Instruct: Code Generation based on the NL-oriented instructions.
The overall statistics of the dataset are as follows:
| Complete | Instruct | |
|---|---|---|
| # Task | 1140 | 1140 |
| # Avg. Test Cases | 5.6 | 5.6 |
| # Avg. Coverage | 99% | 99% |
| # Avg. Prompt Char. | 1112.5 | 663.2 |
| # Avg. Prompt Line | 33.5 | 11.7 |
| # Avg. Prompt Char. (Code) | 1112.5 | 124.0 |
| # Avg. Solution Char. | 426.0 | 426.0 |
| # Avg. Solution Line | 10.0 | 10.0 |
| # Avg. Solution Cyclomatic Complexity | 3.1 | 3.1 |
The function-calling (tool use) statistics of the dataset are as follows:
Structure
default 5,700 rows
| Split | Rows | Size |
|---|---|---|
| v0.1.0_hf | 1,140 | 6.5 MB |
| v0.1.1 | 1,140 | 6.5 MB |
| v0.1.2 | 1,140 | 6.5 MB |
| v0.1.3 | 1,140 | 6.5 MB |
| v0.1.4 | 1,140 | 6.5 MB |
task_idstringcomplete_promptstringinstruct_promptstringcanonical_solutionstringcode_promptstringteststringentry_pointstringdoc_structstringlibsstring
Details
- Repository
- bigcode/bigcodebench
- Publisher
- BigCode
- Task category
- Not stated by the source
- Tags
- croissant, code
- Size category
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- b74c0d0bf70d2c0bc459be537895cca163007f1a
- Last updated
- 2025-04-30
Files
9 files, 16.6 MB in total.
Data7 files · 16.6 MB
Documentation1 file · 8.8 KB
Repository1 file · 2.3 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| data/train-00000-of-00001.parquet | Data | 2.4 MB | ef54cbf5ba83 |
| data/v0.1.0-00000-of-00001.parquet | Data | 2.4 MB | ef54cbf5ba83 |
| data/v0.1.0_hf-00000-of-00001.parquet | Data | 2.4 MB | db28e31fc730 |
| data/v0.1.1-00000-of-00001.parquet | Data | 2.4 MB | 5ac99814c063 |
| data/v0.1.2-00000-of-00001.parquet | Data | 2.4 MB | 323b69f764a2 |
| data/v0.1.3-00000-of-00001.parquet | Data | 2.4 MB | ed5a3a39e011 |
| data/v0.1.4-00000-of-00001.parquet | Data | 2.4 MB | d9a4965821c9 |
| README.md | Documentation | 8.8 KB | — |
| .gitattributes | Repository | 2.3 KB | — |
License and Download
- License
- apache-2.0
- Access
- No access gate
Download from BigCode
Released by BigCode through its official repository on Hugging Face. Read the license.