GTA Benchmark

What is GTA?

GTA is meant for LLM's tool-use evaluations under real-world scenarios, including 229 real-world tasks and executable tool chains.

Released

2024-07-11

Evaluates

智能体, Agent, NeurIPS 2024, 任务执行, Task Execution, 不支持, Unsupported

Openness

open

Importer

OpenCompass Hub

Reported scores

0

Source provenance

• Original evidence https://hub.opencompass.org.cn/dataset-detail/GTA

GTA paper, code and dataset

• Paper https://arxiv.org/abs/2407.08713
• Code https://github.com/open-compass/GTA
• Dataset https://huggingface.co/datasets/Jize1/GTA

Which sources cite GTA?

• GTA

Related 智能体, Agent, NeurIPS 2024, 任务执行, Task Execution, 不支持, Unsupported benchmarks

• A-Bench
• A-OKVQA
• AbsPyramid
• ActionAtlas
• Ada-LEval
• AECBench
• AFQMC
• AgentBoard