evaluating-code-models

Official

Benchmark code generation models.

AuthorOrchestra-Research
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill automates the evaluation of code generation models across a wide array of benchmarks, providing standardized metrics for performance comparison.

Core Features & Use Cases

  • Multi-Benchmark Evaluation: Supports HumanEval, MBPP, MultiPL-E, and over 15 other benchmarks.
  • Pass@k Metrics: Measures functional correctness with industry-standard pass@k metrics.
  • Multi-Language Support: Evaluates models across 18 different programming languages.
  • Use Case: When comparing two new code generation models, use this Skill to run them both against HumanEval and MBPP to objectively determine which performs better.

Quick Start

Evaluate the 'bigcode/starcoder2-7b' model on the HumanEval benchmark.

Dependency Matrix

Required Modules

bigcode-evaluation-harnesstransformers>=4.25.1accelerate>=0.13.2datasets>=2.6.1

Components

scriptsreferences

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: evaluating-code-models
Download link: https://github.com/Orchestra-Research/AI-Research-SKILLs/archive/main.zip#evaluating-code-models

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.