> ## Documentation Index
> Fetch the complete documentation index at: https://openbench.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Coding

> Evaluate AI models on code generation and programming tasks

openbench provides a diverse set of coding benchmarks to assess model capabilities in code generation, problem solving, and software engineering tasks across multiple programming languages.

## Available Benchmarks

<CardGroup cols={2}>
  <Card title="HumanEval" icon="terminal">
    164 hand-written programming problems testing function-level code generation capabilities.

    ```bash theme={null}
    bench eval humaneval
    ```
  </Card>

  <Card title="MBPP" icon="brackets-curly">
    Mostly Basic Programming Problems - entry-level Python programming challenges.

    ```bash theme={null}
    bench eval mbpp
    ```
  </Card>

  <Card title="SciCode" icon="flask">
    Scientific computing problems requiring domain knowledge and programming skills. (Alpha)

    ```bash theme={null}
    bench eval scicode --alpha
    ```
  </Card>

  <Card title="GMCQ" icon="circle-check">
    Graduate-level multiple-choice questions on computer science fundamentals.

    ```bash theme={null}
    bench eval gmcq
    ```
  </Card>

  <Card title="JSONSchemaBench" icon="brackets-curly">
    Tests ability to generate valid JSON outputs conforming to specific schemas.

    ```bash theme={null}
    bench eval jsonschemabench
    ```
  </Card>

  <Card title="Exercism" icon="dumbbell">
    Real-world coding tasks as an agent evaluation across 5 programming languages.

    ```bash theme={null}
    bench eval exercism
    ```
  </Card>
</CardGroup>

<br />

## Related Resources

* [HumanEval Paper](https://arxiv.org/abs/2107.03374)
* [MBPP Dataset](https://github.com/google-research/google-research/tree/master/mbpp)
* [Exercism Platform](https://exercism.org/)