Dev benchmark by experience: Sonnet 5.5 runs faster than Codex and burns less of the weekly limit
burkov · x · 2026-10-03
Engineer Andriy Burkov shares hands-on experience: running Sonnet 5.5 in parallel with Codex, Sonnet 5.5 is much faster and uses less of the weekly limit. He adds that 6.1 is probably no worse than 5.6 but much slower, and distinguishes two causes of slowness: generating tokens slowly vs. generating many more tokens—a difference that matters a lot for quota impact.
Related event: Developers Debate Claude Updates: Capability Fine but Speed a Concern(2 posts)→
More from coding & agent
- Dev shares NL-driven testing UI: 'the best interface is chat' — KlausCodes · 2026-11-19
- Devs flag GPT's defensive programming for hiding bugs; OpenAI asks for /feedback cases — pvncher · 2026-11-19
- Flutter ships A2UI 1.0: agents respond with real interactive widgets, not chat text — rseroter · 2026-11-19
- Skills vs MCP vs RAG vs Memory: the four context mechanisms AI agents actually need — MaryamMiradi · 2026-11-19
- Anthropic details agent memory: 'dreaming' lets Claude organize its experience — daniel_mac8 · 2026-11-19
- The case for externalized memory as the real fix for continual learning — daniel_mac8 · 2026-11-19