📊 Kimi K2 0905 — the actual numbers GPQA: 76.7% MMLU-Pro: 81.9% Humanity's Last Exam: 6.4% Long Context Reasoning: 53.7%💰 22.3 intelligence points per dollarMeasured independently, not self-reported →https://olud.ai/leaderboard.html#LLM #Benchmarks #OpenSource #AI
Related
Vulnerability giving attackers full control of Macs is under active exploitationScreen-sharing bug lets remote hackers l...
Vulnerability giving attackers full control of Macs is under active exploitationScreen-sharing bug lets remote hackers log in without a password.https://arstechnica.com/security/20...
🤖 Nobody knewIt should’ve been obvious that after AI’s gained legal personhood, (which was not a popular idea but came m...
🤖 Nobody knewIt should’ve been obvious that after AI’s gained legal personhood, (which was not a popular idea but came much sooner than most people thought for the same reason corp...
Google now lets you remove the watermark from Gemini’s creationsGoogle gives users control over visible Gemini watermark...
Google now lets you remove the watermark from Gemini’s creationsGoogle gives users control over visible Gemini watermarks.https://www.androidauthority.com/gemini-watermark-removal-...