As of: 2026-11-22 13:32 CET. Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/ Canonical page: https://postcutoff.com/p/x-openaidevs-2122752488558522852/ # “GPT-6.2 Astra sets a new high on Terminal-Bench Science 0.1, which tests how well…” OpenAI Developers (@OpenAIDevs), X, 2026-11-17. Source: https://x.com/OpenAIDevs/status/2122752488558522852 ## Archived text > GPT-6.2 Astra sets a new high on Terminal-Bench Science 0.1, which tests how well models carry out scientific work in a terminal, scoring 9 percentage points higher than GPT-6 Astra at less than 1/3 the cost. Archived 2026-11-18 via fxtwitter (unofficial). Counts: 17,548 views, 95 likes, 5 reposts, 3 replies (at fetch time) Media: https://pbs.twimg.com/media/HXWII8Wa0AAS0b0.png?name=orig ## Cited in - Model: [GPT-6.2 Astra](https://postcutoff.com/m/gpt-6-2-astra/)