Datasets › ToolBench

ToolBench

Introduced by Yujia Qin et al. in ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs31 Jul 2023 archive 2025-07-28

ToolBench is an instruction-tuning dataset for tool use, which is created automatically using ChatGPT. Specifically, the authors collect 16,464 real-world RESTful APIs spanning 49 categories from RapidAPI Hub, then prompt ChatgPT to generate diverse human instructions involving these APIs, covering both single-tool and multi-tool scenarios.

Benchmarks archive 2025-07-28

All 1 leaderboard whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Trajectory Planning ToolBench GPT4-TOPGUN Win rate 86.54 SwissNYF: Tool Grounded LLM Agents for Black Box Setting iclr-dummy-user/swissnyf 3 Compare

Papers archive 2025-07-28

3 shown of 3 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 105. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
SwissNYF: Tool Grounded LLM Agents for Black Box Setting 1 1 15 Feb 2024 ran 2 of 2 samples (0 unverified; 2 pointer-only for licence)
Fortify the Shortest Stave in Attention: Enhancing Context Awareness of Large Language Models for Effective Tool Use 1 1 7 Dec 2023 ran 4 of 4 samples (0 unverified; 4 pointer-only for licence)
ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs 2 1 31 Jul 2023 not harvested

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

License archive 2025-07-28

Apache-2.0 license

Modalities archive 2025-07-28

Languages archive 2025-07-28

Variants archive 2025-07-28

  • ToolBench

1 variant name, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections