Benchmark
ToolAlpaca
A benchmark dataset for evaluating tool-use capability, commonly used to test a model's ability to invoke tools.
Timeline (last 90 days)
Oct 27
This open-source project has been tested on Qwen3.5 and ToolAlpaca.
Unverified50%
A benchmark dataset for evaluating tool-use capability, commonly used to test a model's ability to invoke tools.
This open-source project has been tested on Qwen3.5 and ToolAlpaca.