GPT-6.1 Terra 跑分：Astra 同级 computer use，单任务成本 $0.29 对 $4.82
Agents' Last Exam 上 Terra 与 GPT-6 Astra 同为 57.6%，但每任务 $0.29 对 $4.82；MMMU-Pro 85.5% 接近 Astra 的 86.7%，Terminal-Bench 落后 Sol 和 Sonnet 5.5。
▲ OpenAI just released GPT-6.1 Terra, a fast model that does Astra-level computer use at a fraction of the cost. The key idea is cost per task, not peak score. Terra looks at screens, drawings and photos, reasons at a dial-able effort level, then clicks and types through the computer-use tool. OpenAI tuned it for high-volume work like forms, invoices and technical drawings. On Agents' Last Exam v1 at medium effort, Terra scores 57.6% at $0.29 per task. GPT-6 Astra scores the same 57.6% at $4.82 per task. It also hits 85.5% on MMMU-Pro, close to Astra's 86.7%. It is a trade-off though: on Terminal-Bench 4.0 it solves 50.3%, behind GPT-6.1 Sol (55.9%) and Claude Sonnet 5.5 (70.6%). Available now in the API as gpt-6.1-terra, plus ChatGPT Work and Codex. 1.05M context, closed weights, $1 / $5 per million tokens, half of Sol...... Full analysis: https://www.marktechpost.com/2026/10/26/openai-gpt-6-1-terra/ Announcement: http://openai.com/index/introducing-gpt-6-1-terra Docs: http://developers.openai.com/api/docs/models/gpt-6.1-terra System card: http://deploymentsafety.openai.com/gpt-6-1-terra @OpenAI @OpenAIDevs