New todaygemini-4IMAGE
Gemini 4 Carbon tops index and long context, still trails on coding
Gemini 4 Carbon scores 59 on the index and 96 on long context versus Opus's 67, but still loses to Astra and Opus on FrontierSWE coding and isn't usable yet.
baba yaga
@babayagatwtArchived 6 hours agoOriginally posted 2026.10.29
baba yaga @babayagatwtOriginally posted 2026.10.29
Gemini 4 Carbon just took #1 from Opus and my reactions went all over the place 59 on the index. Argon was at 50 two weeks ago. Ok Google 96 on long context while Opus is at 67. Not even close Then I got to coding and Astra and Opus both still beat it on FrontierSWE And I can't even use it yet
x.com/babayagatwt/status/2115492156148482273Archived 2026.10.29 10:08