From the source
The model scored approximately 72% on internal evals, up from 65% for Opus 4.6.
It follows prompts more closely and is better at complex coding tasks.
From the source
Opus 4.7 now powers Amp's smart mode. In our internal evals, Opus 4.7 scored ~72% , up from Opus 4.6's ~65% - the first model since GPT 5.4 to clear 70%.
ampcode.com