Claude Opus 4.8 scores 58% on DeepSWE coding benchmark, trailing GPT-5.5 but demonstrating lower task costs
Runway’s founder says DeepSWE matches real-world coding impressions.
——0——
It will also be interesting to track how open models close the gap in the coming months.
Epoch AI@EpochAIResearchWe took another look at the capability gap between open-weight and proprietary models. Since the start of the year, open-weight models have lagged the state of the art by four months.
8:01 PM · May 29, 2026 · 203.9K Views
9:03 PM · May 30, 2026 · 2.2K Views