Expired50% confidenceBenchmarkExact time
On the SWE-bench software engineering benchmark, the Claude 3.5 series achieved a significantly higher issue resolution rate than competitors of the same period.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/20/2026
First Seen
Valid until: 10/18/2026(expired)
Sources
Related Claims
UnverifiedClaude 3.5 Sonnet surpassed a 49% solve rate on the SWE-bench software engineering benchmark.71% similarVerifiedClaude 3.5 Sonnet has long led in code benchmarks such as SWE-bench.68% similarUnverifiedIn programming benchmarks, Codex-1 outperformed Claude 3.7 and O3 High.65% similarUnverifiedIn recent hands-on tests, Codex has surpassed Claude Code in multiple evaluation dimensions.64% similarUnverifiedBuddy + Claude Sonnet 4 completed all 3 out of 3 test tasks (100% completion rate), including Lint error fixing, static-to-dynamic data migration, and 3D Context Loss fixing.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/571926API
curl https://kongchang.com/api/v1/knowledge/claims/571926MCP
get_claim(id=571926)