Unverified50% confidenceBenchmarkExact time
GPT-5.6 Extreme High档位约需63美元获得53.6%得分，而Claude Sonnet自适应模式耗费约2000美元得分仅40.5%
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/13/2026
First Seen
Valid until: 10/11/2026
Sources
GPT-5.6发布：三款模型对标Claude，ChatGPT Work超级应用全解析
bilibiliAI-seeker7/9/2026
Related Claims
UnverifiedGPT-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71% similarUnverified在 SWE-bench 测试中，早期 GPT-4 解决率不足 2%，而 Claude 3.5 Sonnet 突破 49%70% similarVerifiedClaude Sonnet 5 在 SWE-bench Verified（Agentic Coding）上得分 63.22%，距 Opus 4.8 约差 6 个百分点69% similarUnverified测试中GLM 5.1综合得分89.3分，排名第一，超过Claude Sonnet 4.6的87.2分68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/501553API
curl https://kongchang.com/api/v1/knowledge/claims/501553MCP
get_claim(id=501553)