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
- Developer Building a Unified Leaderboard of All Model Benchmark Scores — airesearch12 · 2026-09-11
- Rumor claims Kimi faked performance by serving Claude; DeepSeek new model surprises in evals — realsohamparekh · 2026-09-11
- GPT-5.6 writes well but is instantly forgettable, user complains — BasedRaddka · 2026-09-11
- Opus Refuses Protein Research Codebase Over 'Safety' Concerns, Dev Considers Rolling His Own — josephdviviano · 2026-09-11
- User Hails Unconfirmed 'DeepSeek 4.1 Flash' as an Inflection Point in LLMs — himanshustwts · 2026-09-11
- Terminal Bench v4: GLM-5.3 Leads at 41.9%, Kimi-K3 Underwhelms at 12.6% — Ok_Warning2146 · 2026-09-11