Benchmark: new function vs eval vs regular functions

Tests:

Arrow function
var arrowFunc = () => {let r = Math.random().toString(36).substring(7).includes('x');} arrowFunc();
eval
eval("let r = Math.random().toString(36).substring(7).includes('x');");
new function
var newFunc = new Function("let r = Math.random().toString(36).substring(7).includes('x');"); newFunc();
regular function
var regularFunc = function() {let r = Math.random().toString(36).substring(7).includes('x');} regularFunc();

Rendered benchmark preparation results:

Suite status: <idle, ready to run>

Previous results

Test case name	Result
Arrow function
eval
new function
regular function

Fastest: N/A

Slowest: N/A

Latest run results:

Run details: (Test run date: 5 months ago)

User agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/130.0.0.0 Safari/537.36

Browser/OS: Chrome 130 on Linux

View result in a separate tab

Test name	Executions per second
Arrow function	4271899.5 Ops/sec
eval	2281753.5 Ops/sec
new function	1226249.0 Ops/sec
regular function	4335692.0 Ops/sec

Autogenerated LLM Summary (model llama3.2:3b, generated 6 months ago):

LLMs can make mistakes. Check important info.

I'd be happy to explain the benchmark and its various components.

**Benchmark Overview**

The provided JSON represents a JavaScript microbenchmark test case, which is designed to measure the performance of different approaches for creating small functions or expressions in JavaScript. The test case compares three methods:

1. **Arrow function**: A concise syntax introduced in ECMAScript 2015 (ES6) for defining small, single-purpose functions.
2. **eval**: A built-in function that parses and executes a string as JavaScript code.
3. **Regular function**: A traditional way of defining a function using the `function` keyword.

**Options Compared**

The three options are compared in terms of their performance, which is measured by the number of executions per second (ExecutionsPerSecond). The benchmark aims to determine which approach provides the best performance for creating and executing small functions or expressions.

**Pros and Cons of Each Approach**

1. **Arrow function**:
	* Pros: Concise syntax, easier to read and write, and often faster execution due to tree shaking optimization.
	* Cons: Limited support in older browsers (pre-ES6), and some developers may not find it as readable or maintainable.
2. **eval**:
	* Pros: Supports older JavaScript versions, can be used for dynamic code execution, and is widely supported.
	* Cons: Slow performance due to parsing and compilation, security risks if not used carefully, and can lead to bloated bytecode.
3. **Regular function**:
	* Pros: Widely supported in modern browsers, well-established syntax, and often faster execution than eval.
	* Cons: Longer code length compared to arrow functions, which can be less concise.

**Library and Special JS Features**

None of the test cases explicitly use any libraries or special JavaScript features. The benchmark focuses solely on comparing the performance of the three methods.

**Other Considerations**

When writing microbenchmarks like this one, it's essential to consider factors such as:

* **Repeatability**: Ensure that the benchmark is repeatable and consistent across different runs.
* **System load**: Minimize the impact of system load and other external factors on the benchmark results.
* **JavaScript version**: Use a specific JavaScript version or environment to ensure consistency in test results.
* **Browser support**: Test on multiple browsers to account for differences in execution performance.

**Alternatives**

If you're interested in exploring alternative approaches, consider:

* **Lambda functions**: Similar to arrow functions but often used in functional programming languages like Haskell or Scala.
* **Closures**: A concept that uses a function and its local scope to create a new, isolated context.
* **Template literals**: A feature introduced in ES6 for creating string templates with dynamic expressions.

Keep in mind that these alternatives may not be directly comparable to the arrow function, eval, and regular function methods in this specific benchmark.

Related benchmarks:

new function vs eval vs regular functions (version: 0)

Comparing performance of: Arrow function vs eval vs new function vs regular function

Created: 2 years ago by: Guest

Jump to the latest result

Arrow function

eval

new function

regular function

Suite status: <idle, ready to run>

Experimental features:

Fastest: N/A

Slowest: N/A

Autogenerated LLM Summary (model llama3.2:3b, generated 6 months ago):