gpt-6POST
Theo rates Fable 5, Sol, Opus 5.5 and Astra on code, prose, price and intent
Theo scores four models across code capability, prose, price and understanding intent, finding Astra better at code but expensive and the worst at reading intent.
Theo - t3.gg
@theoArchived 2026.10.05Originally posted 2026.10.05
Theo - t3.gg @theoOriginally posted 2026.10.05
More simply put as some vibe rankings Fable 5: - code capability: 7/10 - prose/readability: 6/10 - price: 2/10 - understanding intent: 8/10 GPT-5.6 Sol: - code capability: 6/10 - prose/readability: 7.5/10 - price: 8/10 - understanding intent: 5/10 And now Opus 5.5: - code capability: 9/10 - prose/readability: 8.5/10 - price: 8/10 - understanding intent: 9/10 All improvements! GPT-6 Astra: - code capability: 7.5/10 - prose/readability: 8/10 - price: 3.5/10 - understanding intent: 3/10 Better at code, but worse where it matters
x.com/theo/status/2106847949963800615Archived 2026.10.05 10:05