TUI and CLI for browsing models.dev, benchmarks, coding agents, and statuses for AI providers.
CLI + agent skill for selecting the right LLM based on benchmarks, capabilities, and cost. Works with Cursor, Claude Code, Copilot, and more.
Live LLM API cost calculator & model-comparison tool - compare prices and intelligence across every major model and pick the best value for your workload.
Same intelligence, less money — reads your local Claude Code / Codex / Hermes / OpenCode usage and shows which model gives the same intelligence for less. 100% local, npx, no account.
aicharts plots published AI benchmark scores against cost and tokens per task, and a local collector measures your own agents' token use.
Agent skill for current LLM selection using Artificial Analysis and OpenRouter data: quality, price, speed, context, slugs, and free-tier options. Refreshed daily.
Native Claude Code model and effort router with live modes, timeline, AA evidence and cost receipts. Beta.
AI前沿模型排行:聚合LiveBench/DeepSWE/Artificial Analysis等独立评测,50个旗舰模型通用/写作/性价比三榜,订阅折算+人民币价格,月度自动更新
Daily snapshots of Artificial Analysis AI model leaderboards (LLMs, T2I, T2V, I2V, TTS, Image Editing)
Track 440+ AI model costs and 32+ coding agent plans. Translates obscure tokens/credits into definitive usage metrics, benchmarks, and TOS gotchas.
Compare LLM models using Artificial Analysis data — no API key, stdlib only, with data-quality guards.
Python scraper for Artificial Analysis LLM benchmarks, model pricing, inference speed, and API provider leaderboards. Export complete model comparison data to CSV.
Discovers and evaluates cloud LLM models, judges coding relevance, emits a curated keep-list.
大模型选型表：每日自动聚合 Artificial Analysis 智能指数 × Epoch ECI × 实测成本 | Daily AA × ECI × cost model selection table
AI 大模型第三方权威排行榜聚合：LMArena、Artificial Analysis、LiveCodeBench、SuperCLUE、HF Open LLM。无后端纯静态站，GitHub Actions 每日自动抓取更新，含升降箭头/性价比象限/历史趋势。 | Independent AI model leaderboard aggregator - zero-backend static site, auto-updated daily.
Dark mode userscript for Artificial Analysis, with improved chart, dropdown, and page-surface contrast while preserving provider colors.
Coding agent and model benchmarks, vendor guidance and developer recommendations, with subscription plans and limits
Agent skill: a dated, side-by-side briefing of the Artificial Analysis AI leaderboards (LLMs, coding agents, image, video, speech) with run-over-run change tracking. Fetches via the Bright Data MCP.
Route agent tasks by model, thinking effort, cost, latency, and live Artificial Analysis benchmarks.
To associate your repository with the artificial-analysis topic, visit your repo's landing page and select "manage topics."