Unverified50% confidenceBenchmarkExact time
Grok 4.6在Terminal Bench上的成绩从前代的15%跃升至26%
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
8/15/2026
First Seen
Valid until: 8/29/2026
Sources
Related Claims
UnverifiedGrok 4.5在Terminal Bench 2.1上取得83.3%，超越Opus 4.874% similarUnverifiedGrok 4.6在Deep Suite基准上从54%提升至66%69% similarUnverifiedGrok 4.6的智能指数比Grok 4.5高5分，比Grok 4.3高23分67% similarUnverifiedGrok 4.5在SWE Bench Pro任务上的输出Token比Opus 4.8少4.2倍66% similarUnverifiedGrok 4.6在Frontier Code基准从56.6提升至61.365% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/753868API
curl https://kongchang.com/api/v1/knowledge/claims/753868MCP
get_claim(id=753868)