Unverified50% confidenceFactExact time
评估模型智能体能力的主流基准测试包括BFCL（Berkeley Function Calling Leaderboard）、AgentBench、SWE-Bench；编码能力评测集包括HumanEval、MBPP、LiveCodeBench
1
Sources
50%
Confidence
Long-term
Relevance
8/18/2026
First Seen
Sources
Related Claims
Unverified评估智能体编程能力的主流基准包括SWE-bench、SWE-bench Verified和HumanEval76% similarVerifiedMainstream benchmarks for evaluating programming large models include HumanEval, MBPP, SWE-bench, and LiveCodeBench75% similarUnverifiedThe Berkeley Function-Calling Leaderboard (BFCL) is one of the commonly used benchmarks in the industry for evaluating tool-calling capabilities.73% similarUnverifiedHumanEval, MBPP, and SWE-bench are industry-standard benchmarks in the field of AI programming evaluation.72% similarUnverified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71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/771145API
curl https://kongchang.com/api/v1/knowledge/claims/771145MCP
get_claim(id=771145)