gemini-4IMAGE
OpenAI internal benchmarks show GPT-6.1 Sol ahead of Gemini 4 Argon, post claims
A post with an image claims OpenAI's internal benchmarks show GPT-6.1 Sol crushing Opus 5.5 while Gemini 4 Argon struggles to keep up.
Sashi
@sashikantsingh_Archived 21 days agoOriginally posted 2026.10.15
Sashi @sashikantsingh_Originally posted 2026.10.15
OpenAI's internal benchmarks show GPT-6.1 Sol crushing Opus 5.5, while Gemini 4 Argon is still struggling to keep up 💀
x.com/sashikantsingh_/status/2110649497562796375Archived 2026.10.16 10:10