Customer service and tool use / Benchmark leaderboard
τ³-bench: text and knowledge
Customer service in airline, retail, telecom and banking-knowledge domains; Harbor lists 375 tasks.
No published company result yet.
This benchmark is in the research directory. Its task package, adapter and grading protocol need qualification before a hosted run can be offered.
Arrange an evaluation for your company →What this benchmark measures
Metrics
Domain-specific reward and repeated-run reliability.
Execution requirements
Tool adapter plus user simulation; retrieval setup for knowledge tasks.
Scope and limitations
Banking grading changed in v1.0.1; pin task/evaluator release. The Harbor listing alone does not establish native audio support.
Evaluation availability
Catalog entry. Request a managed evaluation to qualify your agent interface and the benchmark’s native grading requirements.
Sources and company fit
- Original benchmark ↗Current extension
- Harbor · sierra-research/tau3-bench ↗375 source tasks · Public · Public detail metadata + family research
Companies whose products may fit
Research recommendations based on product capabilities. These companies have not necessarily run this benchmark or integrated with Blobfish.
Compatibility notes for each company
Ada: Capability-aligned; adapter/access to qualify
Decagon: Capability-aligned; adapter/access to qualify
Forethought: Capability-aligned; adapter/access to qualify
HubSpot: Product-specific adapter / qualified access
Intercom: Capability-aligned; adapter/access to qualify
Salesforce: Product-specific adapter / qualified access
ServiceNow: Product-specific adapter / qualified access
Sierra: Capability-aligned; adapter/access to qualify
Zendesk: Capability-aligned; adapter/access to qualify