Looking at the row just below the same table, the conclusion is reversed ⚠ ✅ Terminal-bench 2.1: Gemini 3.8 Flash 89.4% vs. Opus 5 89.1%
✅ Terminal-bench 4.0: 19.1% vs. 51.8%, more than double the difference ✅ If it is easy processing, we are more than equal, but if it is difficult processing, we are far apart. For those who want to know more, 👤 Profile → Blog
Genspark announced its first AI model “Gen-1 Slides”🚀
Genspark's first in-house model for knowledge work is now available in AI Slide Standard mode. 🎉 Developed in collaboration with FireworksAI_HQ from an open weight base model. Claude Opus
Claude Opus 5 one shot a Cal AI clone and it COOKED.
Snap a meal -> calories, macros and a blood sugar forecast before you eat I literally just asked it to build a clone using January AI APIs. I expected to find several issues, not a working app. Build time: 67 minutes React
You have reached the end of the archive
All of Claude Opus 5