Controlling Reasoning Effort in LLMs

It has been almost two years since OpenAI released o1, a model that popularized the idea of LLM-based reasoning models. DeepSeek-R1 followed about four months later, together with details of a reinforcement learning with verifiable rewards (RLVR) recipe to train such reasoning models. Last week, OpenAI released the GPT-5.6 model family. It comes in three sizes, each with roughly five or six reasoning-effort settings. Figure 1: The GPT 5.6 Sol model with different reasoning effort settings. (Benchmark numbers for Ultra are currently not available but should be relatively similar to Max, since i.