BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions
Active
Python coding benchmark with 1,140 diverse questions drawing on numerous python libraries.
- Publisher
- Monash University
- Domain
- Coding
- License
- mit
- Published
- Nov 2024
- Notable for
- Benchmark for evaluating Coding.
Cite
Notes
Only stored in your browser.
Related tools
1Implementations, trainers, datasets and scaffolds linked to this eval.
FAQ
- What is BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions?
- Python coding benchmark with 1,140 diverse questions drawing on numerous python libraries.
- How can a model improve its BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions score?
- Tools linked to BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions on Sophon include CODE EDIT RL Env (Community) - RL environments, datasets, and scaffolds that target this eval.
- What license is BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions under?
- BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions is available under mit.