Expired50% confidenceFactExact time
The Claude series of models is developed by Anthropic, and Claude Sonnet 3.5 has a pass rate exceeding 49% on the SWE-bench Verified subset.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/3/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/1/2026(expired)
Sources
Cursor Beginner's Guide: Build a Complete Project with AI from Scratch
bilibili大路朝天qvq6/30/2026
Related Claims
UnverifiedClaude 3.5 Sonnet and the Claude 4 series have performed prominently on authoritative benchmarks such as SWE-bench.77% similarVerifiedThe model used by Cursor in the test is Claude Sonnet 477% similarUnverifiedSonnet is the most balanced model in the Claude family and is currently the most widely used version.74% similarUnverifiedClaude Sonnet 3.7 was released by Anthropic in early 2025 and achieved the highest score at the time on the SWE-bench coding benchmark.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/61826API
curl https://kongchang.com/api/v1/knowledge/claims/61826MCP
get_claim(id=61826)