Unverified60% confidenceBenchmarkExact time
GPT-5.6 Sol在ARC-AGI-2上取得92.5%的成绩
2
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
7/11/2026
First Seen
Valid until: 10/9/2026
Sources
GPT-5.6全解析:Sol旗舰模型性能、短板与竞争力评测
bilibili小牛AI_XNAI7/10/2026
Related Claims
UnverifiedGPT-5.2在ARC-AGI基准测试中登顶83% similarUnverifiedGPT-5.6 Sol在BrowseComp浏览任务基准上达到92.2%81% similarUnverifiedGPT-5.6 Sol在OSWorld 2.0计算机操作基准上达到62.6%,超越Opus 4.8,同时输出Token减少85%79% similarUnverifiedGPT-5.6 Sol在CursorBench上取得了67.2%的得分79% similarVerifiedSOL的基准分数几乎是上一代GPT-5.5的两倍,实现了代际跃升,但整体仍落后于Fable 576% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/486150API
curl https://kongchang.com/api/v1/knowledge/claims/486150MCP
get_claim(id=486150)