τ-Bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
Appears on
Quick read
Latest capture 2026-09-09 03:06
Archive status reflects the last catalog sync, not a maintenance assessment. Check recent releases, issue responses, and fit for your project with the repository shortlisting checklist.
12 paths
Agent instructions and tool configuration found in this repository.
Agent instructions 7
Cursor 5
7 observed captures since 2026-05-25. Observed captures are shown by default.
Stars from first capture +753
Observed captures only
All tracked data
Observed snapshots
Observed snapshots
Nearest indexed repositories by embedding similarity.
Code and Data for Tau-Bench
A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)
A benchmark for LLMs on complicated tasks in the terminal
DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents
Open-source benchmark for browser AI agents on daily tasks.
An agent benchmark with tasks in a simulated software company.
