Claude Opus 5 tops DeepSWE with a 74% score and a claimed 28% cost edge

daniel_mac8 · x · 2026-07-29

Claude Opus 5’s DeepSWE results are now out, and the model is being described as the top long-horizon coding agent on the benchmark.

Related event: Claude Opus 5 Tops DeepSWE Benchmark(2 posts)→

Original post →

More from coding & agent

coding & agent channel →