gemini-4IMAGE
Gemini 4 Argon tops deepswe and automationbench but stays in trusted testing
The post says Gemini 4 Argon ranks first on deepswe and automationbench at 77.9% and 51.3% but remains limited to Google's trusted testers, and that no one it knows is leaving Claude Code or Codex for Antigravity.
Wes Winder
@weswinderArchived 20 days agoOriginally posted 2026.10.10
Wes Winder @weswinderOriginally posted 2026.10.10
gemini 4 argon is #1 on deepswe and automationbench 77.9% and 51.3% but it's still locked behind google's "trusted testers" meanwhile, nobody i know is leaving claude code or codex for antigravity benchmarks literally don't matter. just ship it.
x.com/weswinder/status/2108684231249641580Archived 2026.10.12 10:03