Open LLM Leaderboard

Open LLM Leaderboard is a Hugging Face Space published by the open-llm-leaderboard organization, described as an interactive leaderboard of open-source language models across tests such as IFEval, BBH, MATH, GPQA, MUSR and MMLU-PRO.

Features described on the official site

• The page describes an interactive leaderboard of open-source language models.
• Listed tests include IFEval, BBH, MATH, GPQA, MUSR and MMLU-PRO.
• As a Hugging Face Space it also links files and community discussions.

Suggested starting workflow

• Treat the leaderboard as a reference signal: read what each test measures and compare with your own task.
• When you need a model, return to its model page to check license, size and runtime requirements.
• Re-test with your own examples instead of choosing by rank alone.

These are editorial starting suggestions based on product purpose, not workflows tested by this site.

Before you use it

• Only the page title and description were read; the body loads by script, so leaderboard data, update time and whether it is still updated were not read, and no scores or ranks are copied.
• Leaderboard scores are not tested here and do not predict performance on a specific task; popularity counts such as likes are not cited.
• Benchmark contamination, changes in methodology and the leaderboard's current status follow the official notes and are unverified.