evaluating-code-models

evaluating-code-models is a skill for Claude Code from sangrokjung/claude-forge. It costs 68 tokens per session (3,244 once invoked), scanned A, a copy of evaluating-code-models, MIT.

A benchmarking tool for measuring how well code-generation models solve standard programming tasks across several languages. It reports pass@k, the chance that at least one of several generated answers passes the tests.

In plain words
What is it for?
Use it to run HumanEval, MBPP, MultiPL-E, and other code benchmarks, then review generated solutions and their scores.
Why use it?
It replaces informal impressions of coding ability with repeatable results. This helps compare models and spot differences in language or task performance.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the claude-forge plugin — 33 skills, 39 commands, 17 agents shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/sangrokjung/claude-forge/evaluating-code-models
Any agent
npx skills add sangrokjung/claude-forge --skill evaluating-code-models
Clone the repo
git clone --depth 1 https://github.com/sangrokjung/claude-forge

Made for: Claude Code.

Or install claude-forge, the plugin that ships this one along with the rest of its 33 skills, 39 commands, 17 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for evaluating-code-models

README.md
[![agentmods](https://agentmods.dev/badge/skills/sangrokjung/claude-forge/evaluating-code-models.svg)](https://agentmods.dev/skills/sangrokjung/claude-forge/evaluating-code-models)
Your own site
<a href="https://agentmods.dev/skills/sangrokjung/claude-forge/evaluating-code-models"><img src="https://agentmods.dev/badge/skills/sangrokjung/claude-forge/evaluating-code-models.svg" alt="Measured on agentmods" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,244 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00068 $0.03244
Opus 5 $0.00034 $0.01622
Sonnet 5 $0.00014 $0.00649
Haiku 4.5 $0.00007 $0.00324

Measured 2d ago against content hash 7c46e8eb3ca8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

evaluating-code-models scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

100% identical to evaluating-code-models — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/evaluating-code-models/SKILL.md · 406 lines

How it starts

The opening of the file, as written. The whole thing — 406 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BigCode Evaluation Harness - Code Model Benchmarking

Quick Start

BigCode Evaluation Harness evaluates code generation models across 15+ benchmarks including HumanEval, MBPP, and MultiPL-E (18 languages).

Installation:

git clone https://github.com/bigcode-project/bigcode-evaluation-harness.git
cd bigcode-evaluation-harness
pip install -e .
accelerate config

Evaluate on HumanEval:

accelerate launch main.py \
  --model bigcode/starcoder2-7b \
  --tasks humaneval \
  --max_length_generation 512 \
  --temperature 0.2 \
  --n_samples 20 \
  --batch_size 10 \
  --allow_code_execution \
  --save_generations

View available tasks:

python -c "from bigcode_eval.tasks import ALL_TASKS; print(ALL_TASKS)"

Common Workflows

Workflow 1: Standard Code Benchmark Evaluation

Evaluate model on core code benchmarks (HumanEval, MBPP, HumanEval+).

Checklist:

Code Benchmark Evaluation:
- [ ] Step 1: Choose benchmark suite
- [ ] Step 2: Configure model and generation
- [ ] Step 3: Run evaluation with code execution
- [ ] Step 4: Analyze pass@k results

Step 1: Choose benchmark suite

Python code generation (most common):

  • HumanEval: 164 handwritten problems, function completion
  • HumanEval+: Same 164 problems with 80× more tests (stricter)
  • MBPP: 500 crowd-sourced problems, entry-level difficulty
  • MBPP+: 399 curated problems with 35× more tests

Multi-language (18 languages):

  • MultiPL-E: HumanEval/MBPP translated to C++, Java, JavaScript, Go, Rust, etc.

Advanced:

  • APPS: 10,000 problems (introductory/interview/competition)
  • DS-1000: 1,000 data science problems across 7 libraries

Step 2: Configure model and generation

# Standard HuggingFace model
accelerate launch main.py \
  --model bigcode/starcoder2-7b \
  --tasks humaneval \
  --max_length_generation 512 \
  --temperature 0.2 \
  --do_sample True \
  --n_samples 200 \
  --batch_size 50 \
  --allow_code_execution

# Quantized model (4-bit)
accelerate launch main.py \
  --model codellama/CodeLlama-34b-hf \
  --tasks humaneval \
  --load_in_4bit \
  --max_length_generation 512 \
  --allow_code_execution

# Custom/private model
accelerate launch main.py \
  --model /path/to/my-code-model \
  --tasks humaneval \
  --trust_remote_code \
  --use_auth_token \
  --allow_code_execution

Read the full file on GitHub · 406 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 406 lines · 68 tokens per session scan A 7c46e8eb3ca8

Subscribe to this mod's changes

evaluating-code-models is a skill published in the GitHub repository sangrokjung/claude-forge (824 stars, last pushed 2d ago), licensed MIT. It adds 68 tokens to every session and 3,244 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to evaluating-code-models, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

evaluating-code-models

Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.

davila7/claude-code-templates · 68 tokens

evaluating-code-models

Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.

OpenLAIR/dr-claw · 68 tokens

evaluating-code-models

Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.

synthetic-sciences/openscience · 68 tokens

evaluating-code-models

Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.

foryourhealth111-pixel/Vibe-Skills · 68 tokens

evaluating-code-models

Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.

Orchestra-Research/AI-Research-SKILLs · 68 tokens

evaluating-code-models

Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.

OpenLAIR/dr-claw-plugin-cc · 68 tokens