Mythos 在编程和网络安全基准上碾压 GPT-5.5，做 AI 安全或模型评估的团队需要关注其潜在威胁，建议提前加固防御。
Gary Marcus 引用 scaling01 观点，认为 Mythos 在多项基准测试中优于 GPT-5.5，包括 SWE-bench Pro（77.8% vs 58.6%）、HLE（56.8% vs 41.4%）和网络安全测试。Mythos 在漏洞利用方面表现更强，能更高效地发现安全漏洞，但这也带来严重安全隐患。Marcus 警告，若 Mythos 完全发布，将对未充分防御的现实系统造成巨大混乱。目前最大的未知是 Mythos 在开放真实世界问题中的表现。
1. Agreed w @scaling01 that Mythos appears to be better GPT 5.5 on many metrics. 2. Mythos is defini...
1. Agreed w @scaling01 that Mythos appears to be better GPT 5.5 on many metrics. 2. Mythos is definitely a major wakeup call wrt security, and will pose problems for real-world systems that aren’t well-defended. As @scaling01 says elsewhere a full release of it this point would cause a huge mess. 3. The big open question is how well Mythos does in open-ended real world problems. Lisan al Gaib @scaling01 I don't understand how people are still coping about Mythos. Here's a few benchmarks: SWE-bench Pro: Mythos -> 77.8%, GPT-5.5 -> 58.6% HLE: Mythos -> 56.8%, GPT-5.5 -> 41.4% UK AISI cyber ranges: - "The Last Ones": Mythos -> 6/10, GPT-5.5 3/10 - "Cooling Tower": Mythos -> 3/10, GPT-5.5 0/10 ExploitBench: - Mythos -> 18 Arbitrary Code Executions - GPT-5.5 -> 0 Arbitrary Code Executions ExploitGym: - Mythos -> 157 exploits (289.3 LLM calls) - GPT-5.5 -> 120 exploits (375.4 LLM calls) XBOW same story. Mythos has much higher odds of finding vulnerabilities within smaller token budgets. 🔗 View Quoted Tweet 💬 1 🔄 0 ❤️ 5 👀 3573 📊 2 ⚡