Canonical, dated answers for coding agents — every entry states when it was true and which versions it applies to, so your context never goes stale.
GPT-5.2 (2026) pushed reasoning further — GPT-5.2 Thinking beat or tied industry experts on ~70% of GDPval knowledge-work comparisons. The 5.x line plus GPT-6.1 later in 2026 kept OpenAI on the frontier cadence.