📊 Molmo 7B-D — the actual numbers GPQA: 24% MMLU-Pro: 37.1% Humanity's Last Exam: 5.1% Long Context Reasoning: 0%Measured independently, not self-reported →https://olud.ai/leaderboard.html#LLM #Benchmarks #OpenSource #AI
Related
Writing is thinking. It's one of the reasons I started blogging again and has helped me immensely. Can't recommend it st...
Writing is thinking. It's one of the reasons I started blogging again and has helped me immensely. Can't recommend it strongly enough.AI is still ok for proofreading and mundane ta...
Dew Drop - November 10, 2026 (#4789)https://www.alvinashcraft.com/2026/11/10/dew-drop-november-10-2026-4789/#dotnet #web...
Dew Drop - November 10, 2026 (#4789)https://www.alvinashcraft.com/2026/11/10/dew-drop-november-10-2026-4789/#dotnet #webdev #ai #csharp #windowsdev #cloud #appdev #visualstudio #gi...
"In defense of the human code review"I briefly posted a version of this earlier, but I've retitled, reframed and updated...
"In defense of the human code review"I briefly posted a version of this earlier, but I've retitled, reframed and updated it.It's about the increasing pressures to speed up or repla...