README.md

metadata

title: LLM Explorer
emoji: 🧠
colorFrom: yellow
colorTo: red
sdk: static
pinned: false
license: apache-2.0
short_description: Interactive visualizer — LLM size, speed, benchmarks & price

LLM Explorer

An interactive dashboard comparing 30+ large language models across:

• Benchmarks — MMLU, HumanEval, GSM8K, MATH vs. parameter count
• Speed — tokens/sec vs. parameter count
• Price — cost per million tokens vs. parameter count
• Efficiency — benchmark score per dollar (value frontier)

Data sourced from public leaderboards (Open LLM Leaderboard, Artificial Analysis, provider docs) as of early 2025. Prices reflect API list rates; self-hosted open models show infrastructure-estimated costs.