Unverified50% confidenceBenchmarkExact time
GPT-5.6在网络安全基准上：ExploitBench二代73.5%（上一代47.9%），ExploitGym两小时限制峰值通过率从15.1%提升至24.9%（6小时可达33.7%），CyberSecBench Pro 71.2%（上一代45.8%）
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/11/2026
First Seen
Valid until: 10/9/2026
Sources
GPT-5.6全面开放：Sol/Terra/Luna三档模型与四智能体并行深度解析
bilibili五里墩茶社7/9/2026
Related Claims
UnverifiedGPT-5.6 Sol在ExploitBench网络安全基准上从GPT-5.5的40%跃升至73.5%81% similarUnverifiedGPT-5.6在ExploitBench二代上得73.5%，上一代仅47.9%80% similarUnverifiedGPT-5.6编程能力在关键基准上达到91.9%，安全评测CyberGym得分85.6%，均超越竞品Nexus 580% similarUnverifiedGPT-5.6在ExploitGym两小时限制下峰值通过率从15.1%提升至24.9%，放宽至6小时可达33.7%80% similarUnverified在CyberGym网络安全测试中GPT-5.6以84.5%反超Claude的83.8%76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/476568API
curl https://kongchang.com/api/v1/knowledge/claims/476568MCP
get_claim(id=476568)