Unverified50% confidenceFactExact time
BFCL is a commonly used benchmark for evaluating a model's function calling capability, covering scenarios such as simple functions, multi-function selection, and parameter filling.
1
Sources
50%
Confidence
Long-term
Relevance
10/25/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe Berkeley Function-Calling Leaderboard (BFCL) is one of the commonly used benchmarks in the industry for evaluating tool-calling capabilities.71% similarUnverifiedBFCL is maintained by the Berkeley team, and its evaluation set is stratified by difficulty into categories including Simple, Multiple, Parallel, Parallel Multiple, and Relevance Detection.69% similarUnverifiedOn the two tool-learning benchmarks BFCL v4 and API Bank, SeTPO was compared against three classes of baselines: supervised fine-tuning, reinforcement learning, and distillation.59% similarUnverified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、LiveCodeBench59% similarUnverifiedThe governed approach covers common analytical operations within clearly defined analytical categories, including relational operations, aggregation, comparison, window functions, sorting, and similarity.58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1095142API
curl https://kongchang.com/api/v1/knowledge/claims/1095142MCP
get_claim(id=1095142)