Evaluating Code ModelsSAFE

oh-my-zsh for Claude Code — 16 agents, 35 commands, 32 skills, 21 safety hooks in one install. v4.0 adds an adversarial review loop: a second agent that never sees the first one's reasoning. MIT.

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: evaluating-code-models
description: 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.
version: 1.0.0
author: Orchestra Research
license: MIT
tags: [Evaluation, Code Generation, HumanEval, MBPP, MultiPL-E, Pass@k, BigCode, Benchmarking, Code Models]
dependencies: [bigcode-evaluation-harness, transformers>=4.25.1, accelerate>=0.13.2, datasets>=2.6.1]
---

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

**Evaluate on HumanEval**:
```bash
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**:
```bash
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**

```bash
# 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
```

**Step 3: Run evaluation**

```bash
# Full evaluation with pass@k estimation (k=1,10,100)
accelerate launch main.py \
  --model bigcode/starcoder2-7b \
  --tasks humaneval \
  --temperature 0.8 \
  --n_samples 200 \
  --batch_size 50 \
  --allow_code_execution \
  --save_generations \
  --metric_output_path results/starcoder2-humaneval.json
```

**Step 4: Analyze results**

Results in `results/starcoder2-humaneval.json`:
```json
{
  "humaneval": {
    "pass@1": 0.354,
    "pass@10": 0.521,
    "pass@100": 0.689
  },
  "config": {
    "model": "bigcode/starcoder2-7b",
    "temperature": 0.8,
    "n_samples": 200
  }
}
```

### Workflow 2: Multi-Language Evaluation (MultiPL-E)

Evaluate code generation across 18 programming languages.

**Checklist**:
```
Multi-Language Evaluation:
- [ ] Step 1: Generate solutions (host machine)
- [ ] Step 2: Run evaluation in Docker (safe execution)
- [ ] Step 3: Compare across languages
```

**Step 1: Generate solutions on host**

```bash
# Generate without execution (safe)
accelerate launch main.py \
  --model bigcode/starcoder2-7b \
  --tasks multiple-py,multiple-js,multiple-java,multiple-cpp \
  --max_length_generation 650 \
  --temperature 0.8 \
  --n_samples 50 \
  --batch_size 50 \
  --generation_only \
  --save_generations \
  --save_generations_path generations_multi.json
```

**Step 2: Evaluate in Docker container**

```bash
# Pull the MultiPL-E Docker image
docker pull ghcr.io/bigcode-project/evaluation-harness-multiple

# Run evaluation inside container
docker run -v $(pwd)/generations_multi.json:/app/generations.json:ro \
  -it evaluation-harness-multiple python3 main.py \
  --model bigcode/starcoder2-7b \
  --tasks multiple-py,multiple-js,multiple-java,multiple-cpp \
  --load_generations_path /app/generations.json \
  --allow_code_execution \
  --n_samples 50
```

**Supported languages**: Python, JavaScript, Java, C++, Go, Rust, TypeScript, C#, PHP, Ruby, Swift, Kotlin, Scala, Perl, Julia, Lua, R, Racket

### Workflow 3: Instruction-Tuned Model Evaluation

Evaluate chat/instruction models with proper formatting.

**Checklist**:
```
Instruction Model Evaluation:
- [ ] Step 1: Use instruction-tuned tasks
- [ ] Step 2: Configure instruction tokens
- [ ] Step 3: Run evaluation
```

**Step 1: Choose instruction tasks**

- **instruct-humaneval**: HumanEval with instruction prompts
- **humanevalsynthesize-{lang}**: HumanEvalPack synthesis tasks

**Step 2: Configure instruction tokens**

```bash
# For models with chat templates (e.g., CodeLlama-Instruct)
accelerate launch main.py \
  --model codellama/CodeLlama-7b-Instruct-hf \
  --tasks instruct-humaneval \
  --instruction_tokens "<s>[INST],</s>,[/INST]" \
  --max_length_generation 512 \
  --allow_code_execution
```

**Step 3: HumanEvalPack for instruction models**

```bash
# Test code synthesis across 6 languages
accelerate launch main.py \
  --model codellama/CodeLlama-7b-Instruct-hf \
  --tasks humanevalsynthesize-python,humanevalsynt

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

What the source does

Filesystem

none-observed

Network

none-observed

Shell

none-observed

Dependencies

pinned

Secrets in source

none-found

Findings (0)

No findings outside the package's declared scope.

Gates applied: no_behavioural_pass.