Expired50% confidenceOpinionExact time
Models represented by Claude 3.5 Sonnet have reached engineering-practical levels in code generation pass@1 rates.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/8/2026
First Seen
Valid until: 10/6/2026(expired)
Sources
video-use：AI编程Agent自动剪辑视频的开源利器
githubGitHub Trending7/3/2026
Related Claims
VerifiedClaude 3.5 Sonnet has long led in code benchmarks such as SWE-bench.76% similarVerifiedClaude 3.5 Sonnet achieved a 92% pass rate on the code generation benchmark HumanEval.74% similarUnverifiedClaude 3.5 Sonnet demonstrates outstanding performance in tool-calling accuracy and the reliability of parameter generation.73% similarUnverifiedClaude 3.5 Sonnet surpassed a 49% solve rate on the SWE-bench software engineering benchmark.72% similarUnverifiedClaude Sonnet 4.6 improved from 51% to 59% on the agentic terminal coding benchmark.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/274460API
curl https://kongchang.com/api/v1/knowledge/claims/274460MCP
get_claim(id=274460)