ModelRefs / Open LLM Leaderboard v2 Leaderboard
Open LLM Leaderboard v2 Leaderboard
HuggingFace composite ranking of open-weight models across 6 normalized sub-benchmarks. Current leaders, methodology and sources for Open LLM Leaderboard v2.
Overview
HuggingFace composite ranking of open-weight models across 6 normalized sub-benchmarks.
How it is measured: Average of IFEval + BBH + MATH Lvl5 + GPQA + MuSR + MMLU-Pro; all zero-shot or few-shot per benchmark spec.
How this benchmark is scored
| Category | open-source |
|---|---|
| Maximum score | 100 avg score |
| Direction | Higher is better |
Primary source: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard
Continue your research
Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to Open LLM Leaderboard v2 Leaderboard.
Frequently asked questions
What does the Open LLM Leaderboard v2 benchmark measure?
HuggingFace composite ranking of open-weight models across 6 normalized sub-benchmarks.
What is the methodology?
Average of IFEval + BBH + MATH Lvl5 + GPQA + MuSR + MMLU-Pro; all zero-shot or few-shot per benchmark spec.
Which AI model is the current Open LLM Leaderboard v2 leader?
Phi-4 (Microsoft) currently leads with 30.358128 avg score.