gemini-4VIDEO
Gemini 4 Argon beats Astra after switching to Antigravity Harness
Auditing traces showed Pi Harness ended ~20% of runs at fallbacks such as security tasks; rerunning Gemini 4 Argon with Antigravity Harness put it ahead of Astra and just behind Opus 5.5.
Wenhao Chai
@wenhaocha1Archived 4 days agoOriginally posted 2026.10.26
Wenhao Chai @wenhaocha1Originally posted 2026.10.26
Gemini 4 Argon is underrated 😱. When auditing the traces, we found that Pi Harness just ends the run whenever it hits a fallback (e.g. for security task) in 20% of the runs. We rerun Argon with Antigravity Harness, and now it beats Astra and sits right behind Opus 5.5. Congrats to the team @GoogleDeepMind and looking forward to the new ckpt.
This post quotes another post: x.com/mangqiuyang/status/2113299554317791539
x.com/wenhaocha1/status/2114559544156205413Archived 2026.10.27 09:52