LLM Benchmark Calculator
Compare top language models across industry-standard benchmarks. Filter by use case to find the best model for your project.
| Model | MMLU | HumanEval | HellaSwag | GSM8K | MATH | Score | $/1M tok |
|---|
57-subject knowledge test. Best proxy for general world knowledge and academic reasoning.
Python coding problems. Industry standard for code generation capability (pass@1).
Commonsense NLI completion. Tests physical/social reasoning close to human-level tasks.
Grade-school math word problems. Strong proxy for multi-step reasoning ability.
Competition-level mathematics. Measures advanced mathematical problem-solving.
Weighted average: MMLU 30% + HumanEval 20% + HellaSwag 15% + GSM8K 20% + MATH 15%.
Related Products
on GumroadDeveloper Productivity Bundle
Stop rebuilding the same setup every project. 51 VSCode snippets, 40 Git aliases, 5 Docker Compose stacks, 5 GitHub Actions workflows, 5 README templates, and a dotfiles kit. Set up a professional dev environment in under an hour.
Buy on Gumroad →AI Prompt Engineering Toolkit
58 structured prompt templates for Claude, ChatGPT, and Gemini — organized by use case. Code Review, Debugging, Documentation, Architecture, and 10 model-specific tips. Stop writing prompts from scratch.
Buy on Gumroad →Developer Cheat Sheet Bundle
10 print-ready cheat sheets for the tools developers use every day: Git, Docker, Linux CLI, SQL, Regex, HTTP Status codes, VS Code shortcuts, Bash scripting, jq/JSON, and Markdown.
Buy on Gumroad →You Might Also Need
JSON Formatter & Validator
Format, beautify, and validate JSON online. Paste your JSON to instantly pretty-print it with 2-space, 4-space, or tab indentation. Minify JSON too. Free, runs in your browser.
Open free tool →
Regex Tester
Free regex tester. Test regular expressions against multiple strings with expected match/no-match assertions — see instant pass/fail results. Built-in presets for email, URL, IPv4, and phone. Pro: unl
Open free tool →
Base64 Encoder & Decoder
Free Base64 Encoder & Decoder. Convert text, images, and any file to Base64 and back. Supports URL-safe Base64, image data URIs, and file download from Base64. Runs 100% in your browser — no data sent
Open free tool →
More Free Tools
Related Articles
curl 深度使用手冊：API 測試從入門到進階
curl 是每位開發者必備的 CLI 工具。本文涵蓋 GET/POST/PUT/DELETE 請求、認證、header 設定、檔案上傳、除錯技巧，以及 REST API 測試的完整實戰範例。
Best AI Code Review Tools 2026: CodeRabbit, Sourcery, DeepCode & Bito Compared
Compare top AI code review tools for 2026: CodeRabbit, Sourcery, DeepCode, and Bito. Features, pricing, GitHub/GitLab integration, and choosing the right tool for your team.
AI Code Review Tools 2026: GitHub Copilot, CodeRabbit, Qodo Merge Ranked
Compare AI code review tools for 2026: GitHub Copilot code review, CodeRabbit, Qodo Merge, Sourcery, and PR-Agent. Pricing, accuracy, and GitHub integration.
AI Coding Tools Comparison 2026: GitHub Copilot vs Cursor vs Windsurf vs Cline
Comprehensive comparison of the best AI coding tools in 2026: GitHub Copilot, Cursor, Windsurf, and Cline. Pricing, features, model support, and real-world benchmarks.
AI Pair Programming in 2026: GitHub Copilot vs Cursor vs Claude Code
Master AI pair programming in 2026. Compare GitHub Copilot, Cursor, and Claude Code for autocomplete, chat, and agentic workflows. Includes setup guides and productivity tips.
Enjoying this tool? Get more like it.
Weekly developer tool guides, productivity playbooks & AI tricks. Free. No spam.
Unlock AI-Powered Dev Tools
- ⚡ AI Code Review, Doc Generator & SQL Builder
- ⚡ All premium templates & early access
- ⚡ Member discounts on Gumroad products
$9/mo after trial · Cancel anytime
Want the full toolkit?
Get DevPlaybook Pro
Every template, guide, boilerplate, and automation script in one bundle. 13 premium products — grab them all at once and save big.
MIT licensed · Instant download · No subscription
See what's included → Browse all deals →Frequently Asked Questions
What is MMLU and why does it matter?▼
MMLU (Massive Multitask Language Understanding) tests knowledge across 57 academic subjects including math, science, law, and humanities. It measures breadth of world knowledge and reasoning. A score of 90%+ indicates near-expert level. GPT-4 scores ~86%, Claude 3 Opus ~86%, and Gemini Ultra ~83% on MMLU.
What is HumanEval and how is it measured?▼
HumanEval is a coding benchmark from OpenAI testing 164 Python programming problems. Models are measured on pass@1 (percentage of problems solved correctly on the first try). GPT-4 achieves ~90% pass@1, Claude 3.5 Sonnet ~92%. It's the industry standard for measuring code generation capability.
What is HellaSwag?▼
HellaSwag tests commonsense reasoning by asking models to complete sentences in a way that makes physical and social sense. It's designed to be easy for humans (>95%) but hard for AI. Models scoring above 90% demonstrate strong commonsense understanding. GPT-4 achieves ~95.3%, close to human level.
What does GSM8K measure?▼
GSM8K (Grade School Math 8K) tests multi-step arithmetic reasoning using 8,500 grade-school math word problems. It requires breaking down problems into steps and performing accurate calculations. GPT-4 achieves ~97% on GSM8K. This benchmark correlates strongly with general reasoning ability.
How do I choose the right LLM for my use case?▼
Match benchmarks to your needs: (1) General knowledge tasks → prioritize MMLU. (2) Code generation → prioritize HumanEval. (3) Reasoning/math → prioritize GSM8K and MATH. (4) Long documents → prioritize context window and SCROLLS. (5) Fast responses → prioritize tokens/second. (6) Budget-conscious → balance cost-per-token against performance scores.