OpenAI models write good code but take longer paths; Sol 6.1 is the best worker
haider1 · x · 2026-10-14
A developer's hands-on take on coding models: OpenAI models reliably write good code but sometimes struggle with optimization and take longer paths to solve problems. He calls sol 6.1 the best "worker" model right now — cheaper than opus 5.5, and it follows plans well, especially when you specify data structures and execution flow up front. Meanwhile, astra 6 isn't performing as well as expected.
More from Models
- Claude Max user says Opus 'feels basically unlimited' with stellar quality — soumitrashukla9 · 2026-10-15
- GPT-6 Astra Reads Only 46% of VINs Correctly vs Sonnet 5's 86%: Routing Pays Off — arnabdotorg · 2026-10-15
- VLMs May Turn Clearly Superhuman in Vision Within a Year or Two, Researcher Predicts — arnabdotorg · 2026-10-15
- Gemini 4 Argon Trails GPT 6 Astra by Just 25 Points on Physical Agents Index — qinzytech · 2026-10-15
- GPT-6-Astra scores 98% on unpublished theoretical physics problems, catching expert errors — sandersted · 2026-10-15
- Devs report quality degradation when Kimi K3 is served via third-party providers — casper_hansen_ · 2026-10-15