Cognition(@cognition_labs)
On FrontierCode (Extended), our benchmark for real-world engineering tasks that grades mergeability ...
6.6内容质量
TL;DR · AI 摘要
Cognition on X: "On FrontierCode Extended , our benchmark for real-world engineering tasks that grades mergeability and...
核心要点
- 主题聚焦：On FrontierCode Extended , our benchmark for rea
- 来源：Cognition(@cognition_labs)，建议结合原文判断细节。
- AI 分析暂不可用，本条为保底评分与摘要。
#AI#编程
打开原文Cognition on X: "On FrontierCode (Extended), our benchmark for real-world engineering tasks that grades mergeability and quality, Sonnet 5 scores 53.8% and has a 57.6% pass rate (higher than Opus 4.8). Note: These relative rankings may change slightly with coming adjustments to FrontierCode." / X
Cognition
@cognition
Replying to
On FrontierCode (Extended), our benchmark for real-world engineering tasks that grades mergeability and quality, Sonnet 5 scores 53.8% and has a 57.6% pass rate (higher than Opus 4.8). Note: These relative rankings may change slightly with coming adjustments to FrontierCode.
devin.ai/blog/claude-so…
Claude Sonnet 5 is now available in Devin
From devin.ai
6:21 PM · Jun 30, 2026
4.4K
Views
1
3
31
Read 1 reply