Post-Cutoff

Logan Kilpatrick: Introducing Gemini 4 Carbon, a big jump over Argon (benchmark table)

Logan Kilpatrick @OfficialLoganKXImportance: major (4 of 5)

Why it matters

Gemini API lead’s launch post (~389K views) carrying Google’s full benchmark table against Argon, GPT-6 Astra, Opus 5.5 and Fable 5.1.

Summary

Kilpatrick says Carbon is ‘a big jump over Argon’, SOTA on cyber and long-horizon tasks, #1 on Artificial Analysis V5, better at coding usability and ‘more aligned’. The attached image is Google’s 17-row benchmark table (reproduced in the gemini-4-carbon model file).

Archived text

Introducing Gemini 4 Carbon, it’s a big jump over Argon which we released just 2 weeks ago.

Gemini 4 Carbon is SOTA on cyber, long horizon tasks, ranks #1 on Artificial Analysis V5, significantly improves on usability in domains like coding, and is more aligned.

Source: x.com/OfficialLoganK/status/2115489284404940898Archived 2026-10-28 via fxtwitter (unofficial).Counts: 406,648 views, 9,044 likes, 707 reposts, 777 replies (at fetch time)Media: image

Cited in

  1. Model releases 120 days after the cutoff

    Google announces Gemini 4 Carbon, #1 on the Artificial Analysis Intelligence Index v5 (59), two weeks after Argon; first only for Fairwind cyber defenders