"LLMs are better at writing code to call tools than at calling tools directly." — Cloudflare Code Mode Research

A comprehensive benchmark comparing Code Mode (code generation) vs Traditional Function Calling for LLM tool interactions. Demonstrates that Code Mode achieves 60% faster execution, 68% fewer tokens, and 88% fewer API round trips while maintaining equal accuracy.

Annual Cost Savings: $9,536/year at 1,000 scenarios/day (Claude Haiku pricing)

📊 View Full Results | 📈 Raw Data Tables

• Python 3.11+
• Anthropic API key (for Claude)
• Google API key (for Gemini, optional)

# Clone the repository
git clone <repository-url>
cd codemode_benchmark
# Install dependencies
pip install -r requirements.txt
# Set up environment variables
cp .env.example .env
# Edit .env and add your API keys

# Run full benchmark with Claude
make run
# Run with Gemini
python benchmark.py --model gemini
# Run specific scenario
python benchmark.py --scenario 1
# Run limited scenarios
python benchmark.py --limit 3

codemode_benchmark/
├── README.md                 # This file
├── benchmark.py             # Main benchmark runner
├── requirements.txt         # Python dependencies
├── Makefile                 # Convenient commands
│
├── agents/                  # Agent implementations
│   ├── __init__.py
│   ├── codemode_agent.py           # Code Mode (code generation)
│   ├── regular_agent.py            # Traditional function calling
│   ├── gemini_codemode_agent.py    # Gemini Code Mode
│   └── gemini_regular_agent.py     # Gemini function calling
│
├── tools/                   # Tool definitions
│   ├── __init__.py
│   ├── business_tools.py           # Accounting/invoicing tools
│   ├── accounting_tools.py         # Core accounting logic
│   └── example_tools.py            # Simple example tools
│
├── sandbox/                 # Secure code execution
│   ├── __init__.py
│   └── executor.py                 # RestrictedPython sandbox
│
├── tests/                   # Test files
│   ├── test_api.py
│   ├── test_scenarios.py           # Scenario definitions
│   └── ...
│
├── debug/                   # Debug scripts (development)
│   └── debug_*.py
│
├── docs/                    # Documentation
│   ├── BENCHMARK_SUMMARY.md        # Comprehensive analysis
│   ├── RESULTS_DATA.md             # Raw data tables
│   ├── QUICKSTART.md               # Quick start guide
│   ├── TOOLS.md                    # Tool API documentation
│   ├── CHANGELOG.md                # Version history
│   └── GEMINI.md                   # Gemini-specific notes
│
└── results/                 # Benchmark results
    ├── benchmark_results_claude.json
    ├── benchmark_results_gemini.json
    ├── results.log
    └── results-gemini.log

User Query → LLM → Tool Call #1 → Execute → Result
          ↓
       LLM processes result → Tool Call #2 → Execute → Result
          ↓
       [Repeat 5-16 times...]
          ↓
       Final Response

Problems:

• Multiple API round trips
• Neural network processing between each tool call
• Context grows with each iteration
• High latency and token costs

User Query → LLM generates complete code → Executes all tools → Final Response

Advantages:

• Single code generation pass
• Batch multiple operations
• No context re-processing
• Natural programming constructs (loops, variables, conditionals)

Example:

Regular Agent sees this as 3 separate tool calls:

{"name": "create_transaction", "input": {"amount": 2500, ...}}
{"name": "create_transaction", "input": {"amount": 150, ...}}
{"name": "get_financial_summary", "input": {}}

Code Mode generates efficient code:

expenses = [
    ("rent", 2500, "Monthly rent"),
    ("utilities", 150, "Electricity")
]
for category, amount, desc in expenses:
    tools.create_transaction("expense", category, amount, desc)
summary = json.loads(tools.get_financial_summary())
result = f"Total: ${summary['summary']['total_expenses']}"

The benchmark includes 8 realistic business scenarios:

1. Monthly Expense Recording - Record 4 expenses and generate summary
2. Client Invoicing Workflow - Create 2 invoices, update status, summarize
3. Payment Processing - Create invoice, process partial payments
4. Mixed Income/Expense Tracking - 7 transactions with financial analysis
5. Multi-Account Management - Complex transfers between 3 accounts
6. Quarter-End Analysis - Simulate 3 months of business activity
7. Complex Multi-Client Invoicing - 3 invoices with partial payments (16 operations)
8. Budget Tracking - 14 categorized expenses with analysis

Each scenario includes automated validation to ensure correctness.

class CodeModeAgent:
    def run(self, user_message: str) -> Dict[str, Any]:
        # 1. Send message with tools API documentation
        response = self.client.messages.create(
            system=self._create_system_prompt(),  # Contains tools API
            messages=[{"role": "user", "content": user_message}]
        )
        # 2. Extract generated code
        code = extract_code_from_response(response)
        # 3. Execute in sandbox
        result = self.executor.execute(code)
        return result

from typing import TypedDict, Literal
class TransactionResponse(TypedDict):
    status: Literal["success"]
    transaction: TransactionDict
    new_balance: float
def create_transaction(
    transaction_type: Literal["income", "expense", "transfer"],
    category: str,
    amount: float,
    description: str,
    account: str = "checking"
) -> str:
    """
    Create a new transaction.

    Returns: JSON string with TransactionResponse structure

    Example:
        result = tools.create_transaction("expense", "rent", 2500.0, "Monthly rent")
        data = json.loads(result)
        print(data["new_balance"])  # 7500.0
    """
    # Implementation...

Code execution uses RestrictedPython for sandboxing:

• No filesystem access
• No network access
• No dangerous imports
• Controlled builtins

Key Insight: Code Mode advantage scales with complexity, but even simple tasks benefit significantly.

(Based on Claude Haiku pricing: $0.25/1M input, $1.25/1M output)

• Model: Claude 3 Haiku
• Performance: 60.4% faster, 68.3% fewer tokens
• Best For: Cost-sensitive production workloads
• Status: ✅ Fully tested (8/8 scenarios)

• Model: Gemini 2.0 Flash Experimental
• Performance: 15.1% faster, 70.6% fewer iterations
• Best For: Low-latency requirements
• Status: ✅ Partially tested (2/8 scenarios)
• Note: Faster baseline but more verbose code generation

# Run all tests
make test
# Run specific test file
python -m pytest tests/test_scenarios.py
# Test Code Mode agent directly
python agents/codemode_agent.py
# Test Regular Agent directly
python agents/regular_agent.py
# Test sandbox execution
python sandbox/executor.py

• Benchmark Summary - Comprehensive analysis with insights
• Results Data - Raw performance tables
• Quick Start Guide - Step-by-step setup
• Tools Documentation - Available tools and API
• Changelog - Version history
• Gemini Notes - Gemini-specific information

1. Batching Advantage

   • Single code block replaces multiple API calls
   • No neural network processing between operations
   • Example: 16 iterations → 1 iteration (Scenario 7)

2. Cognitive Efficiency

   • LLMs have extensive training on code generation
   • Natural programming constructs (loops, variables, conditionals)
   • TypedDict provides clear type contracts

3. Computational Efficiency

   • No context re-processing between tool calls
   • Direct code execution in sandbox
   • Reduced token overhead

✅ Multi-step workflows - Greatest benefit with many operations ✅ Complex business logic - Invoicing, accounting, data processing ✅ Batch operations - Similar actions on multiple items ✅ Cost-sensitive workloads - Production at scale ✅ Latency-critical applications - User-facing systems

1. Use TypedDict for response types - Provides clear structure to LLM
2. Include examples in docstrings - Shows correct usage patterns
3. Batch similar operations - Leverage loops in code
4. Validate results - Automated checks ensure correctness
5. Handle errors gracefully - Try-except in generated code

Contributions are welcome! Please:

1. Fork the repository
2. Create a feature branch (git checkout -b feature/amazing-feature)
3. Make your changes
4. Run tests (make test)
5. Commit (git commit -m 'Add amazing feature')
6. Push (git push origin feature/amazing-feature)
7. Open a Pull Request

• Cloudflare Code Mode Blog Post
• Anthropic Building Effective Agents
• Claude API Documentation
• Gemini API Documentation
• RestrictedPython Documentation

MIT License - See LICENSE file for details

• Inspired by Cloudflare's Code Mode research
• Built on Anthropic's Building Effective Agents framework
• Uses RestrictedPython for secure code execution

For questions or feedback, please open an issue on GitHub.

Benchmark Date: January 2025 Models Tested: Claude 3 Haiku, Gemini 2.0 Flash Experimental Test Scenarios: 8 realistic business workflows Result: Code Mode is 60% faster, uses 68% fewer tokens, with equal accuracy