Benchmark

API-Bank

A comprehensive benchmark for tool-augmented LLMs that evaluates API planning, retrieval, and calling capabilities. Contains 314 tool-use dialogues with…

Modality
text
Categories
reasoning, tool_calling
Openness
unknown
Source
llm_stats
Reported scores
3

Reported scores

llm_stats

ModelOrganizationReported valueReportedEvidence
Llama 3.1 405B InstructMeta0.922024-07-23evidence
Llama 3.1 70B InstructMeta0.92024-07-23evidence
Llama 3.1 8B InstructMeta0.8262024-07-23evidence

Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.