Unverified60% confidenceBenchmarkExact time
On standard code benchmarks such as HumanEval and MBPP, top open-source models have already reached 85–95% of the performance level of closed-source models.
2
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
8/16/2026
First Seen
Valid until: 11/14/2026
Sources
Freebuff：免费AI编程代理挑战Cursor、Claude Code和Devin
producthuntProductHunt Daily8/14/2026
Related Claims
Unverified传统代码评测基准（如HumanEval、MBPP）主要测试模型在孤立函数级别的生成准确率72% similarUnverifiedOpen-source models' performance on benchmarks has increasingly approached, and in some tasks even surpassed, that of closed-source models.71% similarVerifiedMainstream benchmarks for evaluating programming large models include HumanEval, MBPP, SWE-bench, and LiveCodeBench71% similarUnverified当前主流基准测试体系如HumanEval、MBPP等代码评估集往往关注平均性能，对分布式的场景特定退化现象敏感度不足69% similarUnverifiedCommonly used evaluation benchmarks for measuring the gap between open-source and closed-source models include HumanEval/SWE-bench for coding ability, MATH and GPQA for reasoning ability, and MMLU for overall performance.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/757075API
curl https://kongchang.com/api/v1/knowledge/claims/757075MCP
get_claim(id=757075)