Claude Opus 4.8 has landed on DeepSWE Bench, posting a 58% Pass@1 and taking #2 overall behind GPT-5.5. It continues a broader trend: slightly behind on raw score, but among the most reliable and efficient coding models across recent benchmarks.
X (formerly Twitter) ·
Claude Opus 4.8 has landed on DeepSWE Bench, posting a 58% Pass@1 and taking #2 overall behind GPT-5.5. It continues a broader trend: slightly behind on raw score, but among the most reliable and efficient coding models across recent benchmarks.