@lord.luke5: gemini 4 carbon just took #1 on the Artificial Analysis Intelligence Index with a 59 claude opus 5.5 is right behind at 58 gpt-6 astra is at 57 gemini 4 argon is at 50 and claude fable 5.1 is at 49 it's only a 1 point lead so i wouldn't switch everything over yet google's own table has gemini 4 carbon winning most of the other benchmarks too but opus 5.5 still wins OSWorld at 87.2% and gpt-6 astra wins FrontierSWE 2 at 65.5% scores are cool but i care more about how it does in real work which model are you using the most right now

Unc Luke

Open In TikTok:

Region: US

Thursday 29 October 2026 02:05:13 GMT