OpenAI Teases Upcoming Cyber Model Scoring 79.1% on Internal PatchBench, Beating GPT-6 Cyber
JiaweiLiu_ · x · 2026-11-13
OpenAI researcher Jiawei Liu teased an upcoming "cyber model" trained to be good at patching, sharing an internal PatchBench chart: GPT-6 Astra at 71.1%, GPT-6 Cyber at 73.5%, and the upcoming model at 79.1%. The team says it improved patching ability and internal PatchBench (Nate Andre) results, continuing OpenAI's streak of cybersecurity-focused model teasers.
Related event: OpenAI teases cyber model scoring 79.1% on PatchBench, beating GPT-6(2 posts)→
More from Models
- Chinese major models reportedly trained on Blackwell-class chips, though scale disappoints — teortaxesTex · 2026-11-13
- One user burned $4,988 of API-priced tokens on a $200 Claude subscription last month — jonathan_wilke · 2026-11-13
- Gemini 4 Hydrogen tops Google models on AA-Robotics v0.1, ranking fourth overall — ArtificialAnlys · 2026-11-13
- 4,689-trial agent test: DeepSeek V4 argues its way into failures, Gemini 3.8 Flash fails silently — Kindly-Bag763 · 2026-11-13
- Analyst: DeepSeek V4's Flash variant is winning, and a hyper-efficient 2B V5 could be the real play — teortaxesTex · 2026-11-13
- Interaction-as-a-Judge beats code rewards: +6.7pp win rate, 35.7% less code bloat — arena · 2026-11-13