Unverified50% confidenceBenchmarkExact time
Kimi K2 performs prominently on multiple programming benchmarks including SWE-bench and HumanEval.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
8/16/2026
First Seen
Valid until: 11/14/2026
Sources
Related Claims
UnverifiedKimi K3 performs nearly on par with Anthropic and OpenAI flagship models across multiple benchmarks including front-end design and software engineering, and outperforms them in some tests.63% similarUnverified评估智能体编程能力的主流基准包括SWE-bench、SWE-bench Verified和HumanEval61% similarUnverifiedKimi Code's Goal mode (/go command) supports multi-round iteration, and K2.7 Code has been specifically optimized for Goal mode.61% similarUnverifiedHumanEval, MBPP, and SWE-bench are standard benchmark datasets specifically targeting code generation.61% similarVerifiedMainstream benchmarks for evaluating programming large models include HumanEval, MBPP, SWE-bench, and LiveCodeBench60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/758717API
curl https://kongchang.com/api/v1/knowledge/claims/758717MCP
get_claim(id=758717)