Codesota · Tasks · Tool UseHome/Tasks/Agentic AI/Tool Use

Tool Use.

Benchmarks measuring AI agents ability to use tools and APIs to complete real-world tasks across domains like retail and airline customer service.

1
Datasets
8
Results
Canonical metric
§ 02 · Canonical benchmark

The reference dataset.

Seeking canonical benchmark for this task.

Suggest one →
§ 03 · Top 10

Leading models.

Leading models across all datasets in this task.

#Modelpass_rateYearSource
Claude Opus 4.579.0paper ↗
2GPT-5.273.0paper ↗
3Gemini 3 Pro69.0paper ↗
4Claude Sonnet 4.563.0paper ↗
5GPT-5.159.0
6Gemini 2.5 Pro54.0
7Claude 3.7 Sonnet47.0
8GPT-4o36.0

What were you looking for on Tool Use?

Didn't find the model, metric, or dataset you needed? Tell us in one line. We read every message and reply within 48 hours.

§ 04 · All datasets

Tracked datasets.

1 dataset tracked for this task.

Tau2-Bench
8 results · pass_rate
Top: Claude Opus 4.5 79.0
§ 05 · Related tasks

Other tasks in Agentic AI.

Agent MemoryAutonomous CodingBioinformatics AgentsHCASTRE-BenchSWE-benchTask agentsTime Horizon
Reply within 48 hours · No newsletter

Didn't find what you came for?

Still looking for something on Tool Use? A missing model, a stale score, a benchmark we should cover — drop it here and we'll handle it.

Real humans read every message. We track what people are asking for and prioritize accordingly.