GPT-6 Astra已在模型选择器中出现
6 Astra is starting to show up in the model picker 👀
OpenAI的GPT-6 Astra来了,数学、科学、网络安全等多项测试创下新高,Greg Brockman称已进入AGI时代。
OpenAI发布了GPT-6 Astra模型,在ARC-AGI 3基准测试中达到98.6%,远超5.6 Sol的7.8%。该模型在Exploit-Bench网络安全测试中获得100%满分,在FrontierMath Tier 4(v2)中得分为97.6%,优于Fable 5.1的87.8%。DeepSWE v1.1测试中,GPT-6 Astra得分为74.1%,高于Fable 5.1的67.4%。
6 Astra is starting to show up in the model picker 👀
6 Astra is starting to show up in the model picker 👀 The Rundown AI @TheRundownAI GPT-6 Astra is here, with OpenAI calling it “a generational leap in capability”. A few of the headline benchmarks: - ARC- AGI 3 – 98.6% (!), compared to 7.8% for 5.6 Sol - Exploit-Bench (cybersecurity) - 100% (!) - FrontierMath Tier 4 (v2) - 97.6%, vs. 87.8% for Fable 5.1 - DeepSWE v1.1 - 74.1%, vs. 67.4% for Fable 5.1 New highs for the industry across math, science, health, computer use, coding, cybersecurity, and more. OpenAI's Greg Brockman: "Welcome to the AGI era." 🔗 View Quoted Tweet 💬 4 🔄 0 ❤️ 9 👀 2577 📊 4 ⚡