Unverified50% confidenceFactExact time
据称 Grok 4.5 的 token 效率约为同类领先模型的两倍，能用不到一半的步骤完成任务
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/11/2026
First Seen
Valid until: 10/9/2026
Sources
Grok 4.5 实测：更快更便宜的编码黑马，能否取代 Opus 与 GPT？
youtubeForrestKnight7/10/2026
Related Claims
UnverifiedGrok 4.5在SWE Bench Pro任务上的输出Token比Opus 4.8少4.2倍76% similarUnverifiedGrok 4.6的智能指数比Grok 4.5高5分，比Grok 4.3高23分67% similarUnverifiedClaude Opus 4.8 completed identical tasks with 15% fewer steps and 35% fewer output tokens compared to its predecessor65% similarUnverifiedGrok 4.5在Terminal Bench 2.1上取得83.3%，超越Opus 4.865% similarUnverifiedGrok 4.5 是一个1.5万亿参数的 MoE 模型，此前的 Grok 只有5000亿参数64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/487942API
curl https://kongchang.com/api/v1/knowledge/claims/487942MCP
get_claim(id=487942)