Opus 5

wbk ᕦ(ò_ó )ᕤAug 15

Grok 4.6 passed Claude Fable 5, Claude Opus 4.8, Gemini 3.1 Pro, GPT-5.5 and GPT-5.6 Sol on EEBench, an electrical engineering benchmark.

First time I see such a clear gap between top models in this type of test.

The DOOM GuyAug 151

AI tried to recreate american gothic and found a detail that was never in the prompt

Claude Fable 5, Opus 5 and GPT Sol were given the same task: recreate Grant Wood’s famous painting step by step inside a single HTML file But Fable 5 went further. Before drawing the pitchfork,

Mikadzyki🌙Aug 159

Four models, same scene.

Grok 4.6 finished last, behind Opus 5, Qwen 3.8 Max and GLM 5.3 Max. look at the clocks though. Grok finished in roughly 15 minutes. Opus took about 45. three times faster and fourth on looks. in a one-shot beauty contest that reads as a loss, and it is

88n77Aug 155