Anthropic Models Steadily Improve on Multimodal Coding Benchmark, 90% Within Reach

jyangballin · x · 2026-09-01

Developer jyangballin comments that debugging GitHub issues communicated with visuals (not text) remains partially unsolved in 2026. Since Opus 4.7, Anthropic models have steadily climbed in multimodal performance. He believes reaching 90%+ on this benchmark is just a matter of time.

Original post →

More from Models

Models channel →