Open LLM Leaderboard
The Open LLM Leaderboard is Hugging Face's public benchmark ranking open large language models; its v2 revision introduced harder benchmarks and normalized scoring.
Coverage of Hugging Face's Open LLM Leaderboard — how open models are benchmarked and ranked, including the v2 overhaul that made scores fairer and harder to game.
Latest coverage
Articles
NewsThis Week in AI: June 24–30
NewsHugging Face's Open LLM Leaderboard v2 increases difficulty and delivers fairer scores
AI MakerspaceAligning LLMs: DPO
NewsThe Allen Institute for AI (AI2) released OLMo 7B and the OLMo framework
NewsMistral AI wants to lead the open generative AI community
NewsAnyscale announces collaboration with Meta to accelerate development of the Llama 2 ecosystem