Unverified60% confidenceBenchmarkExact time
Grok 4.5在SWE-Bench Pro上取得64.7%,反超GPT Live 1和GPT 5.5
2
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
7/11/2026
First Seen
Valid until: 10/9/2026
Sources
GPT Live全双工、Grok 4.5编程、Seedream 5.0图像:AI三赛道同步提速
bilibili养老院killer7/9/2026
Related Claims
UnverifiedGrok 4.5在Terminal Bench基准测试中取得83.3%,基本与GPT 5.5打平,略低于Claude 582% similarUnverified在编码能力上 Grok 4.5 与 Opus 4.8、GPT 5.5 基本持平,但响应速度最快77% similarUnverifiedGrok 4.5生成的Minecraft克隆版在所有顶尖模型中排名第三,前两名分别是Fable 5和GPT 5.577% similarUnverifiedGPT-5.6在Terminal-Bench 2.1编码榜单上以Ultra配置取得91.9%的成绩75% similarUnverifiedGrok 4.5能力尚未完全达到Claude 5或GPT 5.5的级别,但在能力、延迟和价格三者之间取得了平衡72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/488369API
curl https://kongchang.com/api/v1/knowledge/claims/488369MCP
get_claim(id=488369)