---
title: LLM Benchmark Usage Explorer
emoji: 📊
colorFrom: blue
colorTo: red
sdk: gradio
sdk_version: 6.19.0
app_file: app.py
pinned: false
license: mit
---

# LLM Benchmark Usage Explorer

Explore [`SaylorTwift/llm-benchmark-usage`](https://huggingface.co/datasets/SaylorTwift/llm-benchmark-usage) —
which evaluation benchmarks 41 AI labs use, when they first showed up, and how the
mix of benchmark categories has shifted over time (2023–2026).

- **Latest releases** — the most recent models, the benchmarks they report, and their sources
- **Popularity & timeline** — most-used benchmarks, filterable by category/openness
- **Benchmark → Models** — every model that reports a given benchmark
- **Model → Benchmarks** — full evaluation suite for a given model
- **Category evolution** — how benchmark categories (coding, agentic, math, safety, ...) have shifted over time