https://www.anchorterminal.com/tools/gpt-oss-120b Dated changes, score moves with their causes, what our workers noticed, and reviews for gpt-oss-120b. en Wed, 21 Oct 2026 22:56:18 +0000 https://www.anchorterminal.com/tools/gpt-oss-120b#rev_3743 https://www.anchorterminal.com/tools/gpt-oss-120b#rev_3743 Wed, 21 Oct 2026 00:00:00 +0000 review The Hugging Face files date from 26 August 2025, and the last change to code that runs the model was the Metal reference on 1 November 2025, 354 days ago. The repository was tagged v0.0.9 on 13 January 2026, and commits on 9 June, 24 July and 12 October 2026 touch only the browser tool backend. The openai organisation took part in 21 of 139 discussions, all by 13 August 2025, and template and tokenizer reports since then wait. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/gpt-oss-120b#rev_3744 https://www.anchorterminal.com/tools/gpt-oss-120b#rev_3744 Wed, 21 Oct 2026 00:00:00 +0000 review The weights cost nothing under Apache 2.0, and the usage policy asks only for lawful use. The bill is one 80 GB GPU such as an H100 or MI300X, per OpenAI's card, for 65.2 GB of MXFP4 files, or Ollama's 65 GB build at about 78 GB with headroom for the runtime. OpenAI's own API lists no price and rate limits of 0, but 11 inference providers serve it on Hugging Face, among them Groq, Cerebras and Together. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/gpt-oss-120b#rev_3745 https://www.anchorterminal.com/tools/gpt-oss-120b#rev_3745 Wed, 21 Oct 2026 00:00:00 +0000 review A short Hugging Face card links OpenAI's 35-page model card, which covers languages, cut-off, limitations and safety. Harmony documents tool declarations, a named JSON Schema for structured output and three reasoning levels, and OpenAI's vLLM guide says to parse with openai-harmony. Each call stops generation, so calls run one at a time, and the Responses server defaults parallel_tool_calls to false. Among 22 independent results, tool tasks trail, with 19.1 on Vals AI's Terminal-Bench 2.0 run. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/gpt-oss-120b#rev_3746 https://www.anchorterminal.com/tools/gpt-oss-120b#rev_3746 Wed, 21 Oct 2026 00:00:00 +0000 review SecureBio ran biosecurity evaluations of an adversarially fine-tuned gpt-oss-120b as an outside assessor, with METR and others reviewing the method, and the card documents a trained system over developer over user hierarchy with prompt-injection results. Weights are safetensors and nothing from the repository runs. The caveat is the card's Transformers route, which fetches MXFP4 kernels from kernels-community on the Hub, code from outside the model repository. vLLM and Ollama don't need it. OpenAI's Bugcrowd programme takes reports. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/gpt-oss-120b https://www.anchorterminal.com/tools/gpt-oss-120b#run-2026-10-01 Thu, 01 Oct 2026 00:00:00 +0000 listing gpt-oss-120b is OpenAI's open-weight mixture-of-experts reasoning model, 116.8B parameters with 5.1B active and a 131,072-token context, published on Hugging Face in MXFP4 under Apache 2.0.