Leaked Claude Opus 5 Takes 50% Longer Than Opus 4.8 in AA-Briefcase Tasks
ArtificialAnlys · x · 2026-07-25
According to Artificial Analysis evaluation data, the recently surfaced Claude Opus 5 shows a significant increase in processing time for complex tasks under high-effort settings.
- Longer Duration: Across its top three effort settings (max, xhigh, high), Opus 5 averages 36.2, 34.3, and 25.7 minutes per task.
- Comparison: At max effort, this is roughly 50% longer than Opus 4.8 (24.1 minutes).
- More Turns: The increased time is primarily driven by a surge in reasoning turns. Opus 5 averages 103, 91, and 76 turns across its top three effort levels, compared to just 55 for Opus 4.8.
More from Models
- supermemory unveils learner-1, claiming continual learning for any model — julianweisser · 2026-10-26
- Anthropic says Opus 5.5 cuts cost per task by ~40% vs Opus 5 — taufiqintech · 2026-10-26
- AI search APIs ranked: top 12 within 7 points, yet prices differ nearly 7x — FinanceYF5 · 2026-10-26
- OpenAI Dots coming to EU/EEA and UK in a few weeks, slides confirm — testingcatalog · 2026-10-26
- OpenAI Dots demoed live as EU launch speculated, Codex adoption in Germany revealed — testingcatalog · 2026-10-26
- "Abliterated models just have brain damage" — community pushes back on unaligned model hype — dhadfieldmenell · 2026-10-26