Search
OpenAI Embraces ComplexFuncBench to Assess GPT-4.1 Model Capabilities
2025-04-15 /
Read about 0 minute
Author：小编
OpenAI has integrated ComplexFuncBench into its latest GPT-4.1 series of models to rigorously evaluate their function calling prowess. Developed by the Zhipu team, ComplexFuncBench is tailored to assess the competence of large models in executing complex function calls. This benchmark meticulously focuses on the performance of these models in multi-step, contextually constrained function calls within a 128K-length context. In contrast to existing benchmarks, ComplexFuncBench challenges models to demonstrate a more nuanced comprehension of real-world user needs and to execute multi-step, reasoning-based function calls, thereby setting a higher bar for evaluating the models' functional capabilities.
-
C114 Communication Network -
Communication Home
7 X 24 Track global technological trends
