OpenAI Blog
Sep 21
V7 cuts costs 78% while boosting accuracy with GPT-5.6 Luna
Using GPT-5.6, V7 turns scattered company files into context agents can use to complete complex, source-linked work.
Basis completes a tax workbook 2x faster with GPT-6 Astra
Related stories
OpenAI Blog
5d ago
Introducing GPT-6.1 Sol
OpenAI introduces GPT‑6.1 Sol, a new model described as near‑Astra intelligence for coding, computer use, and professional work. It offers these capabilities at one‑fifth of Astra’s standard API input and output token prices, implying a more cost‑effective solution for developers and businesses.
OpenAI Blog
Sep 3
Legora reviewed 41 documents in minutes with GPT-6 Astra
Legora employed GPT‑6 Astra to review 41 documents in just minutes, successfully identifying all four planted errors. The use of the model also led to a nearly 40% improvement in performance within this financial‑review workflow.
OpenAI Blog
Sep 25
Proaction boosts sales 60% and saves 75+ hours with Codex
Proaction leverages Codex, GPT‑Live‑1, and GPT‑6 Astra to accelerate the development, operation, and sales of modern fleet management solutions, achieving a 60% increase in sales and saving over 75 hours of work.
OpenAI Blog
Sep 9
GPT-6 Astra: The next generation in intelligence for work
OpenAI introduces GPT‑6 Astra, its most capable model for business. The new model boasts advanced reasoning, computer use, and improved writing and design judgment. It is positioned as the next generation of intelligence for work.
OpenAI Blog
Aug 21, 2025
Scaling domain expertise in complex, regulated domains
Discover how Blue J is transforming tax research with AI-powered tools built on GPT-4. 1.
arXiv AI
Sep 25
SheetMind: Actions Set Accuracy, Agents Set the Failure Mode
SheetMind is a Manager‑Action‑Reflection framework that evaluates how much spreadsheet agent performance derives from the agents themselves versus the shared action interface. In a controlled study on all 221 tasks of the SheetCopilot Benchmark, replacing the high‑level action API with primitive cell operations drops accuracy by 47.1 points, while adding a Reflection Agent improves performance by 4.5 points and a Manager by 1.4 points. The framework also shows that decomposition changes failure modes, reducing silent wrong outputs from 33% to 25%, and that GPT‑5 and GPT‑5‑mini achieve similar performance, whereas GPT‑3.5 underperforms significantly.
OpenAI Blog
Sep 22
Better prompt caching for GPT-6
The OpenAI Blog announces that GPT‑6 enhances prompt caching, achieving higher cache hit rates and introducing new diagnostics, explicit breakpoints, and controls. These features are designed to reduce latency and costs for users. The post highlights the technical improvements that make GPT‑6 more efficient and cost‑effective.
OpenAI Blog
Aug 10
Model ML completes finance work more efficiently with GPT-5.6 Sol
Model ML uses GPT-5. 6 Sol to carry finance work from research and analysis through editable, traceable PowerPoint decks and Excel workbooks.
arXiv AI
Aug 18
Skill Blocks: How Should an Agent Load Its Skill? A Caching-Correct Comparison of Pre-load, On-Demand Tool-Loading, Progressive Disclosure, and Hybrid
arXiv:2608. 14943v1 Announce Type: new Abstract: Agent skills are often injected in full on every request, increasing token cost.
arXiv AI
Jul 3
Office Comprehension Benchmark
arXiv:2607. 01245v1 Announce Type: cross Abstract: We introduce Office Comprehension Bench (OCB), the first public benchmark to jointly evaluate LLM systems on Word, Excel, and PowerPoint comprehension over native file formats (.
OpenAI Blog
Sep 11
Cognition helps Devin test its own work with GPT‑6 Astra
The OpenAI Blog article titled "Cognition helps Devin test its own work with GPT‑6 Astra" discusses how GPT‑6 Astra enhances Devin’s capability to test software and demonstrate its functionality. This improvement aims to enable engineers to review less code and accelerate shipping of products.