https://x.com/EMostaque/status/2082600218529235174

After deployment, we applied GPT-5.6 Sol to advance the frontier of efficiency by making itself more efficient to run. The results: - 20% lower serving costs from production GPU kernel improvements. - 15%+ better token-generation efficiency from improved speculative decoding.

Source: Emad Mostaque (X) | 2026-07-29