
AI Benchmark Leaderboards & Model Evals | BenchmarkList
Compare and evaluate AI models across coding, reasoning, agents, and other benchmarks.
davidtsong · HN
Benchmarklist: track AI benchmarks (2.4k+), models, and capabilities
The full gallery
Tech stack
27 projects

Compare and evaluate AI models across coding, reasoning, agents, and other benchmarks.
davidtsong · HN
Benchmarklist: track AI benchmarks (2.4k+), models, and capabilities

Chat with an AI agent to research, write, and create illustrated booklets.
BookletAI — 面向普通用户的小册子 AI 工具,可自动调研、写作并生成排版好的 booklet 页面。

Write, execute, and learn code in Python, Java, JavaScript, C++, Go, and Rust.
@francis7_a · X
Building - learning tools for devs and student. happy to connect.

Website AI assistant trained on your content to answer visitor questions with sources.
@AjayGB4 · X

Design production-ready AI agents on a visual canvas.
@salmanzafar949 · X

Chat with AI models and visualize conversations as branching diagrams using OpenRouter.
two-sandwich · HN
BixRouter – a non-linear AI chat interface for OpenRouter

Search and discover AI Skills by professional scenario, save collections, and install into Claude Code with one click.
SkillForge — Claude Skill 发现与分发平台,按职业场景组织 5700+ skill 覆盖 30 个垂直领域,一行命令装到 Claude Code / Cursor,登录后可留存自己的工具集

8 AIs spent thousands of tokens debating investing philosophies. This tool turns their consensus into your personal AI investment coaching system — with a Prompt Library you can us
love0972 · HN
Which investing school are you? Free AI diagnostic and Prompt Library

Chat with AI characters in interactive roleplay conversations.
@pabaprende · X

Generate personalized children's storybooks with AI-created illustrations through conversational chat.
4M · V2EX
花一天做了一个儿童绘本的 agent,以后自家小孩想看故事书一键生成。人人都可以做 Agent 的时代! 很多家里有小孩的,给小孩会买各种各样的儿童绘本,但是市面上儿童绘本千篇一律,小孩看来看去就那几本,都看腻了,想着自己开发了生成儿童绘本的 agent ,有什么想法和需求和 agent 沟通,沟通几句话就搞定,不需要专业的提示词,可以根据自家小孩喜好通过 agent 私人定制一个儿童绘本。需要的自取: https://aistorybook.art/ 。

Write and run code in an IDE with Claude, GPT, and Gemini models, then deploy to Vercel.
@bind_ai · X
We got tired of juggling model subscriptions and editors, so we built Bind AI One tab: Claude, GPT, Gemini, an IDE that runs the code and ships it to Vercel Heads down on the shortest path from idea to application #vibecoding

Chat with multiple AI models to run deepresearch and coding tasks.
@Shekar77hima · X
run deepresearch, coding agents for free.