Expired50% confidenceBenchmarkExact time
Even the strongest models on SWE-Bench can only solve approximately 50% of the problems.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
8/16/2026
First Seen
Valid until: 8/30/2026(expired)
Sources
Meta开源Muse-Glimmer-30B模型：Agent能力全面对标Qwen，本地部署指南
Related Claims
VerifiedCurrently, the resolution rate of top models on the SWE-bench Verified subset has exceeded 50%.77% similarUnverified按任务难度合理匹配模型能力，仅这一步就能砍掉50%以上的Token开支71% similarUnverifiedWhen SWE-bench was first released, the pass rate of top models was below 2%; the pass rate of leading systems has now surpassed 50%.71% similarUnverifiedOn SWE-bench, early models had a solve rate below 5%, while mainstream products in 2025 have surpassed 50%.70% similarUnverifiedSWE-bench is a benchmark measuring models' ability to autonomously fix real GitHub Issues; early models had a resolution rate below 5%, and by 2025 mainstream products have surpassed 50%.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/757573API
curl https://kongchang.com/api/v1/knowledge/claims/757573MCP
get_claim(id=757573)