Unverified50% confidenceBenchmarkExact time
四轮测试中Astra拿下三胜、动态图形打平，测评者判定GPT-6整体领先
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/11/2026
First Seen
Valid until: 12/10/2026
Sources
Related Entities
Related Claims
Unverified在Agents' Last Exam评测中，GPT-5.6 Sol取得53.6分，比采用自适应推理的Claude Fable 5高出13.1分70% similarUnverified四项实测中Astra赢下三项（堡垒之夜复刻、旅游着陆页、3D地球仪仪表盘），动态图形讲解打平70% similarUnverifiedGPT-5.6在Agent's Last Exam测试中以53.6分创下历史新高，领先Claude Opus 4.5达13.1分68% similarUnverified在Terminal Bench 2.1基准测试上，GPT-5.6 Sol的Ultra模式接近92%，超越竞品的88%表现64% similarUnverified在四个大型项目构建测试中，Fable拿下两次明确胜利加一次小胜，一次打平63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/909325API
curl https://kongchang.com/api/v1/knowledge/claims/909325MCP
get_claim(id=909325)