We have been testing GPT-5.5 in early access. Our evals show it’s the most capable model for people...

Our evals show it’s the most capable model for people taking on complex builds with technical depth.

• 23.1% fewer tool calls per request • 10% better at breaking through roadblocks • 12.5% higher scores on our hardest benchmarks https://t.co/Y1RWycnDNW" / X

Post

Conversation


We have been testing GPT-5.5 in early access. Our evals show it’s the most capable model for people taking on complex builds with technical depth. • 23.1% fewer tool calls per request • 10% better at breaking through roadblocks • 12.5% higher scores on our hardest benchmarks at the same cost


New to X?

Sign up now to get your own personalized timeline!

Trending now

What’s happening

Trending in United States

Tornado Watch

Technology · Trending

GPT-5.5

Trending in United States

Prince Harry

Sports · Trending

Brandon Marsh