JEV is king at categorization!

🚨 JEV beats the TOP embedder (Qwen3-Embedding-4B) at categorization! 46% vs 97% accuracy! Not a simple win! We benchmarked +1000 TODO titles: - JEV scored 97% accuracy compared to Opus 5 reference. Qwen3 only 46%! - Embedder costed

Marcell HavlikSep 198

Claude Opus 5 vs Gemini 4 vs GPT-6 Astra vs Grok 4.6

I handed the same unfinished drawing to four different AI models and said "be creative." Rumoured Gemini 4 checkpoint is inside Arena. four completely different pandas came out. and I genuinely can't pick a favorite 👇

Poonam SoniSep 1943

Gemini 4 pro VS opus 5 🤯

Arena testers ran the same Three.js 3D prompt across both models: • Opus 5: Basic low-poly mesh • Gemini 4 Pro: Coherent spatial depth & mesh topology • Full interactive WebGL export Google is dominating 3D code.

Web3BitsSep 19

Tried the exact prompt “hey Opus 5, search the web, download images you liked, and then doodle on them using JavaScript” on Opus 5

Here’s the output I got.

agim𓍯Sep 1912