Unverified50% confidenceBenchmarkExact time
在Terminal Bench 2.1基准测试上，Ultra模式接近92%，超越竞品的88%表现
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/20/2026
First Seen
Valid until: 10/18/2026
Sources
Related Claims
Unverified当所有模型在某评测上都能拿90分时该评测就应退场，即基准饱和现象62% similarUnverifiedo1在国际数学奥林匹克级别问题上正确率超过80%，远高于GPT-4的约13%62% similarUnverified国赛查重率标准：超20%不评省一/国一，超40%无奖，超60%通报批评62% similarUnverifiedRocky在SWE-verified 100道题测试中两轮平均约80分，接近DeepSeek-V4-Pro官方的80+分62% similarUnverifiedMax级别相比extra high最多多消耗两倍的token，但在各类基准测试中仅带来4%至10%的性能提升61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/572658API
curl https://kongchang.com/api/v1/knowledge/claims/572658MCP
get_claim(id=572658)