Granite 4.0 1B: GPQA 28.1%, MMLU-Pro 32.5%, HLE 4.8%, Long Context 6% — measured independently, not self-reported. For a 1B, that spread is the reality. Open bench page for full picture.https://olud.ai/leaderboard.html#LLM #Benchmarks #OpenSource #AI
Related
We want consequences that aren't just a cost of doing business.#AI #Accountability
We want consequences that aren't just a cost of doing business.#AI #Accountability
I also suspect they'll just move the site, not change their minds about AI data centres.We need a much clearer message t...
I also suspect they'll just move the site, not change their minds about AI data centres.We need a much clearer message to be sent to the State and Federal governments! Australia do...
#Salinas #School District to dump #Meta over #AI and student #privacy concerns:https://www.ksbw.com/article/salinas-scho...
#Salinas #School District to dump #Meta over #AI and student #privacy concerns:https://www.ksbw.com/article/salinas-school-district-delete-social-media-accounts-ai/74380873