leo 🐾@synthwaveddGemini 3.6 Flash benchmarks are out, and it's... beaten by other models on code tasks, and is only really consistently SoTA on vision and context benchmarks. But hey, 3.1 Pro is now so old 3.6 Flash outperforms it across the board 😭Opens with an observation
leo 🐾@synthwaveddOpenAI have today published a blog post detailing the precautions they're taking with regard to Astra's capabilities and the necessary safeguards Yet another good sign it's imminent! You can give it a read here - t.coOpens with an observation
leo 🐾@synthwaveddcan't help but notice every new chinese model's benchmark visuals seem to compare to previous generations opus 4.7 conspicuously absent.. lolOpens with an observation