Press Space to continue
GPT 5.5 loses to Opus 4.7 on software engineering benchmarks
Press Space to continue
GPT 5.5 underperforms Opus 4.7 on SWE-Bench Pro. Couldn't find any reported SWE-Bench scores at all and an internal benchmark is reported instead. That footnote is trying really hard to bury the lede. GPT 5.5 isn't SOTA for coding.
open on x · 2 views · 1 clickViews and clicks count once per visitor per day. Clicks are opens of this post on X.