10:59
2026-08-11
floatboat.ai
artificial-intelligence
Claude Opus 4.8 Costs 57.1× More, Loses All 5 Benchmarks – Beaten by the Harness
Floatboat's V4-Flash model, evaluated by its own Floatboat Evaluation Harness, achieved top rankings on five third-party benchmarks, including first place on Toolathlon (79.62) and third on BrowseComp…