OpenAI: gpt-oss-20b

GPT-OSS-20B is a text-in, text-out model from OpenAI with a 131,072-token context window. It supports tool use and reasoning, making it applicable to multi-step workflows and agentic pipelines. Structured output support is unconfirmed from available data. There is no published maximum completion length, which is worth clarifying with the vendor before deploying it in output-heavy applications. At $0.029 per million input tokens and $0.14 per million output tokens, the pricing sits in a budget-to-mid range tier. Its blended benchmark score of 23.8 across only four benchmarks provides limited confidence in that figure, so treat it as a preliminary signal rather than a settled verdict. The coding score (34.1) outpaces the agentic score (5.1) noticeably, so teams evaluating it for code-adjacent tasks have more evidence to work with than those considering autonomous agent use cases.