I ran the same 5 real tests on every current Claude model

Fable 5.2, Fable 5.1, Opus 5.5, Sonnet 5.5 and Haiku 5.5. Same prompts. Identical computers. Judged blind by a non-Claude model. The newest, most expensive model did not win. Tests by petergyang. Full video:

Smelter Labs AINov 10

5. The same "Cathedral of Ice" Blender prompt on Fable 5.2 vs Opus 5.5.

The Fable run took 1h 56m and cost $81.10.

The AI FieldNov 10

Elon Musk just gave a huge update on Grok 5

Grok 5 is expected to surpass Claude Opus 5.5 in performance, potentially within just 2–3 months And thereafter, it won't just be Claude models setting the standard. Grok models are going to be pushing the boundaries of what's

RRRNov 10

Finally, after resetting the 5-hour limit three times, Claude Fable 5.2 finished its Gummy Bear version.

This exceeded my expectations and is much better and fun than the Opus 5.5 version. Watch it and have fun. 🤣

ArkNov 10