GPT-6 Sol
OpenAI · September 22, 2026
● activeClosedmixture of expertsmultimodal
Context Window1M tokens
Description
The high-efficiency frontier workhorse of the GPT-6 generation, delivering parity with late GPT-5.6 models at 50% lower serving costs.
Benchmark Scores
MMLUMassive Multitask Language Understanding — 57 subjects
91.5%HumanEvalCode generation pass@1 — Python problems
94.2%MATHMATH benchmark — competition-level problems
95.8%SWE-benchReal-world software engineering
68.5%Key Innovations
Reasoning
ReasoningStructured step-by-step problem solving, often using chain-of-thought or tree-of-thought approaches.
Agentic
AgenticModels that can autonomously plan, execute multi-step tasks, use tools, and self-correct without human intervention.
Tool Use
Tool UseAbility to call external tools, APIs, and functions — enabling web browsing, code execution, and real-world actions.
MoE
MoEArchitecture where only a fraction of the model's parameters are active for each input, allowing massive scale with lower compute.