OpenAI's Astra Aces ExploitBench with Massive Exploit Gains

OpenAI's upcoming safety model Astra scored 100% on ExploitBench and 39% exploit success on 20 high-severity vulnerabilities, 3.4x better than GPT-5.6. OpenAI has also resumed some large-scale frontier RL runs that were previously paused.

2026-09-02 ~ 2026-09-02 · 4 related posts

• OpenAI Resumes Large-Scale Frontier RL Training as Astra Scores Perfect in Tests — haider1 · 2026-09-02
• Astra hits 100% success on ExploitBench refresh, reaching 'cyber-critical' threshold — infoxiao · 2026-09-02
• New model 'Astra' claims massive improvement over GPT-5.6 on ExploitBench — daniel_mac8 · 2026-09-02
• OpenAI Astra achieves 3.4x exploit success rate vs GPT-5.6 with 45% fewer tokens — imjustnewatai · 2026-09-02