A "quiet" 0.1 update just beat OpenAI's newest flagship model.
No big launch name. No hype cycle. Just a version bump that quietly doubled its own predecessor on the hardest science test out there. Here's what happened → Anthropic dropped Claude Fable 5.1 (and its
Gemini 3.8 flash is actually insane, better output than opus 5, better understanding of lighting and shaders.
This is no threejs, it's actual GdShader inside godot, working flawlessly. Absolute legend of a model, more testing soon.
OpenAI & Anthropic CEOs watching Gemini 3.8 Flash launch right now...
Fable 5.1 launched yesterday - Gemini 3.8 drops within 24 hours 💀 - Beats Opus 5 across many benchmarks - 59 on Artificial Analysis Intelligence Index - Just 7 points behind Fable 5.1 - 13× cheaper at
I asked Gemini 3.8 flash and Opus 5 to each build me a light house scene, same exact prompt.
This was the output. I don't mind that gemini got some colors off because the output was decent. The difference? Gemini finished in 55 seconds. Opus 5 took 32 minutes and absolutely
You have reached the end of the archive
All of Claude Opus 5