# tau3-bench - domain: customer-service - n_tasks: 375 - n_runnable: 0 - owner_org: Sierra - grading: state-check - task_kind: tool-agent-user conversations (airline, retail, telecom, banking_knowledge) - url_repo: https://github.com/sierra-research/tau2-bench - url_paper: https://arxiv.org/abs/2603.04370 ## Tasks | task | difficulty | language | runnable | harnesses tried | |---|---|---|---|---| | [tau3-airline-0](https://harnessreport.com/tasks/tau3-bench/tau3-airline-0.md) | medium | | | 0 | | [tau3-airline-1](https://harnessreport.com/tasks/tau3-bench/tau3-airline-1.md) | medium | | | 0 | | [tau3-airline-10](https://harnessreport.com/tasks/tau3-bench/tau3-airline-10.md) | medium | | | 0 | | [tau3-airline-11](https://harnessreport.com/tasks/tau3-bench/tau3-airline-11.md) | medium | | | 0 | | [tau3-airline-12](https://harnessreport.com/tasks/tau3-bench/tau3-airline-12.md) | medium | | | 0 | | [tau3-airline-13](https://harnessreport.com/tasks/tau3-bench/tau3-airline-13.md) | medium | | | 0 | | [tau3-airline-14](https://harnessreport.com/tasks/tau3-bench/tau3-airline-14.md) | medium | | | 0 | | [tau3-airline-15](https://harnessreport.com/tasks/tau3-bench/tau3-airline-15.md) | medium | | | 0 | | [tau3-airline-16](https://harnessreport.com/tasks/tau3-bench/tau3-airline-16.md) | medium | | | 0 | | [tau3-airline-17](https://harnessreport.com/tasks/tau3-bench/tau3-airline-17.md) | medium | | | 0 | | [tau3-airline-18](https://harnessreport.com/tasks/tau3-bench/tau3-airline-18.md) | medium | | | 0 | | [tau3-airline-19](https://harnessreport.com/tasks/tau3-bench/tau3-airline-19.md) | medium | | | 0 | | [tau3-airline-2](https://harnessreport.com/tasks/tau3-bench/tau3-airline-2.md) | medium | | | 0 | | [tau3-airline-20](https://harnessreport.com/tasks/tau3-bench/tau3-airline-20.md) | medium | | | 0 | | [tau3-airline-21](https://harnessreport.com/tasks/tau3-bench/tau3-airline-21.md) | medium | | | 0 | | [tau3-airline-22](https://harnessreport.com/tasks/tau3-bench/tau3-airline-22.md) | medium | | | 0 | | [tau3-airline-23](https://harnessreport.com/tasks/tau3-bench/tau3-airline-23.md) | medium | | | 0 | | [tau3-airline-24](https://harnessreport.com/tasks/tau3-bench/tau3-airline-24.md) | medium | | | 0 | | [tau3-airline-25](https://harnessreport.com/tasks/tau3-bench/tau3-airline-25.md) | medium | | | 0 | | [tau3-airline-26](https://harnessreport.com/tasks/tau3-bench/tau3-airline-26.md) | medium | | | 0 | | [tau3-airline-27](https://harnessreport.com/tasks/tau3-bench/tau3-airline-27.md) | medium | | | 0 | | [tau3-airline-28](https://harnessreport.com/tasks/tau3-bench/tau3-airline-28.md) | medium | | | 0 | | [tau3-airline-29](https://harnessreport.com/tasks/tau3-bench/tau3-airline-29.md) | medium | | | 0 | | [tau3-airline-3](https://harnessreport.com/tasks/tau3-bench/tau3-airline-3.md) | medium | | | 0 | | [tau3-airline-30](https://harnessreport.com/tasks/tau3-bench/tau3-airline-30.md) | medium | | | 0 | | [tau3-airline-31](https://harnessreport.com/tasks/tau3-bench/tau3-airline-31.md) | medium | | | 0 | | [tau3-airline-32](https://harnessreport.com/tasks/tau3-bench/tau3-airline-32.md) | medium | | | 0 | | [tau3-airline-33](https://harnessreport.com/tasks/tau3-bench/tau3-airline-33.md) | medium | | | 0 | | [tau3-airline-34](https://harnessreport.com/tasks/tau3-bench/tau3-airline-34.md) | medium | | | 0 | | [tau3-airline-35](https://harnessreport.com/tasks/tau3-bench/tau3-airline-35.md) | medium | | | 0 | | [tau3-airline-36](https://harnessreport.com/tasks/tau3-bench/tau3-airline-36.md) | medium | | | 0 | | [tau3-airline-37](https://harnessreport.com/tasks/tau3-bench/tau3-airline-37.md) | medium | | | 0 | | [tau3-airline-38](https://harnessreport.com/tasks/tau3-bench/tau3-airline-38.md) | medium | | | 0 | | [tau3-airline-39](https://harnessreport.com/tasks/tau3-bench/tau3-airline-39.md) | medium | | | 0 | | [tau3-airline-4](https://harnessreport.com/tasks/tau3-bench/tau3-airline-4.md) | medium | | | 0 | | [tau3-airline-40](https://harnessreport.com/tasks/tau3-bench/tau3-airline-40.md) | medium | | | 0 | | [tau3-airline-41](https://harnessreport.com/tasks/tau3-bench/tau3-airline-41.md) | medium | | | 0 | | [tau3-airline-42](https://harnessreport.com/tasks/tau3-bench/tau3-airline-42.md) | medium | | | 0 | | [tau3-airline-43](https://harnessreport.com/tasks/tau3-bench/tau3-airline-43.md) | medium | | | 0 | | [tau3-airline-44](https://harnessreport.com/tasks/tau3-bench/tau3-airline-44.md) | medium | | | 0 | | [tau3-airline-45](https://harnessreport.com/tasks/tau3-bench/tau3-airline-45.md) | medium | | | 0 | | [tau3-airline-46](https://harnessreport.com/tasks/tau3-bench/tau3-airline-46.md) | medium | | | 0 | | [tau3-airline-47](https://harnessreport.com/tasks/tau3-bench/tau3-airline-47.md) | medium | | | 0 | | [tau3-airline-48](https://harnessreport.com/tasks/tau3-bench/tau3-airline-48.md) | medium | | | 0 | | [tau3-airline-49](https://harnessreport.com/tasks/tau3-bench/tau3-airline-49.md) | medium | | | 0 | | [tau3-airline-5](https://harnessreport.com/tasks/tau3-bench/tau3-airline-5.md) | medium | | | 0 | | [tau3-airline-6](https://harnessreport.com/tasks/tau3-bench/tau3-airline-6.md) | medium | | | 0 | | [tau3-airline-7](https://harnessreport.com/tasks/tau3-bench/tau3-airline-7.md) | medium | | | 0 | | [tau3-airline-8](https://harnessreport.com/tasks/tau3-bench/tau3-airline-8.md) | medium | | | 0 | | [tau3-airline-9](https://harnessreport.com/tasks/tau3-bench/tau3-airline-9.md) | medium | | | 0 | | [tau3-banking_knowledge-task-001](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-001.md) | medium | | | 0 | | [tau3-banking_knowledge-task-002](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-002.md) | medium | | | 0 | | [tau3-banking_knowledge-task-003](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-003.md) | medium | | | 0 | | [tau3-banking_knowledge-task-004](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-004.md) | medium | | | 0 | | [tau3-banking_knowledge-task-005](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-005.md) | medium | | | 0 | | [tau3-banking_knowledge-task-006](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-006.md) | medium | | | 0 | | [tau3-banking_knowledge-task-007](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-007.md) | medium | | | 0 | | [tau3-banking_knowledge-task-008](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-008.md) | medium | | | 0 | | [tau3-banking_knowledge-task-010](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-010.md) | medium | | | 0 | | [tau3-banking_knowledge-task-012](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-012.md) | medium | | | 0 | | [tau3-banking_knowledge-task-014](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-014.md) | medium | | | 0 | | [tau3-banking_knowledge-task-015](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-015.md) | medium | | | 0 | | [tau3-banking_knowledge-task-016](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-016.md) | medium | | | 0 | | [tau3-banking_knowledge-task-017](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-017.md) | medium | | | 0 | | [tau3-banking_knowledge-task-018](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-018.md) | medium | | | 0 | | [tau3-banking_knowledge-task-019](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-019.md) | medium | | | 0 | | [tau3-banking_knowledge-task-020](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-020.md) | medium | | | 0 | | [tau3-banking_knowledge-task-021](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-021.md) | medium | | | 0 | | [tau3-banking_knowledge-task-022](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-022.md) | medium | | | 0 | | [tau3-banking_knowledge-task-023](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-023.md) | medium | | | 0 | | [tau3-banking_knowledge-task-024](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-024.md) | medium | | | 0 | | [tau3-banking_knowledge-task-025](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-025.md) | medium | | | 0 | | [tau3-banking_knowledge-task-026](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-026.md) | medium | | | 0 | | [tau3-banking_knowledge-task-027](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-027.md) | medium | | | 0 | | [tau3-banking_knowledge-task-028](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-028.md) | medium | | | 0 | | [tau3-banking_knowledge-task-029](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-029.md) | medium | | | 0 | | [tau3-banking_knowledge-task-031](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-031.md) | medium | | | 0 | | [tau3-banking_knowledge-task-032](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-032.md) | medium | | | 0 | | [tau3-banking_knowledge-task-033](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-033.md) | medium | | | 0 | | [tau3-banking_knowledge-task-034](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-034.md) | medium | | | 0 | | [tau3-banking_knowledge-task-035](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-035.md) | medium | | | 0 | | [tau3-banking_knowledge-task-036](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-036.md) | medium | | | 0 | | [tau3-banking_knowledge-task-037](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-037.md) | medium | | | 0 | | [tau3-banking_knowledge-task-038](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-038.md) | medium | | | 0 | | [tau3-banking_knowledge-task-039](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-039.md) | medium | | | 0 | | [tau3-banking_knowledge-task-040](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-040.md) | medium | | | 0 | | [tau3-banking_knowledge-task-041](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-041.md) | medium | | | 0 | | [tau3-banking_knowledge-task-043](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-043.md) | medium | | | 0 | | [tau3-banking_knowledge-task-044](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-044.md) | medium | | | 0 | | [tau3-banking_knowledge-task-045](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-045.md) | medium | | | 0 | | [tau3-banking_knowledge-task-046](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-046.md) | medium | | | 0 | | [tau3-banking_knowledge-task-047](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-047.md) | medium | | | 0 | | [tau3-banking_knowledge-task-048](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-048.md) | medium | | | 0 | | [tau3-banking_knowledge-task-049](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-049.md) | medium | | | 0 | | [tau3-banking_knowledge-task-050](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-050.md) | medium | | | 0 | | [tau3-banking_knowledge-task-051](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-051.md) | medium | | | 0 | | [tau3-banking_knowledge-task-052](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-052.md) | medium | | | 0 | | [tau3-banking_knowledge-task-053](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-053.md) | medium | | | 0 | | [tau3-banking_knowledge-task-054](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-054.md) | medium | | | 0 | | [tau3-banking_knowledge-task-055](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-055.md) | medium | | | 0 | | [tau3-banking_knowledge-task-056](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-056.md) | medium | | | 0 | | [tau3-banking_knowledge-task-057](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-057.md) | medium | | | 0 | | [tau3-banking_knowledge-task-058](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-058.md) | medium | | | 0 | | [tau3-banking_knowledge-task-059](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-059.md) | medium | | | 0 | | [tau3-banking_knowledge-task-060](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-060.md) | medium | | | 0 | | [tau3-banking_knowledge-task-061](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-061.md) | medium | | | 0 | | [tau3-banking_knowledge-task-062](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-062.md) | medium | | | 0 | | [tau3-banking_knowledge-task-063](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-063.md) | medium | | | 0 | | [tau3-banking_knowledge-task-064](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-064.md) | medium | | | 0 | | [tau3-banking_knowledge-task-065](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-065.md) | medium | | | 0 | | [tau3-banking_knowledge-task-066](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-066.md) | medium | | | 0 | | [tau3-banking_knowledge-task-067](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-067.md) | medium | | | 0 | | [tau3-banking_knowledge-task-068](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-068.md) | medium | | | 0 | | [tau3-banking_knowledge-task-069](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-069.md) | medium | | | 0 | | [tau3-banking_knowledge-task-070](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-070.md) | medium | | | 0 | | [tau3-banking_knowledge-task-071](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-071.md) | medium | | | 0 | | [tau3-banking_knowledge-task-072](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-072.md) | medium | | | 0 | | [tau3-banking_knowledge-task-073](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-073.md) | medium | | | 0 | | [tau3-banking_knowledge-task-074](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-074.md) | medium | | | 0 | | [tau3-banking_knowledge-task-075](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-075.md) | medium | | | 0 | | [tau3-banking_knowledge-task-076](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-076.md) | medium | | | 0 | | [tau3-banking_knowledge-task-077](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-077.md) | medium | | | 0 | | [tau3-banking_knowledge-task-078](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-078.md) | medium | | | 0 | | [tau3-banking_knowledge-task-079](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-079.md) | medium | | | 0 | | [tau3-banking_knowledge-task-080](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-080.md) | medium | | | 0 | | [tau3-banking_knowledge-task-081](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-081.md) | medium | | | 0 | | [tau3-banking_knowledge-task-082](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-082.md) | medium | | | 0 | | [tau3-banking_knowledge-task-083](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-083.md) | medium | | | 0 | | [tau3-banking_knowledge-task-084](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-084.md) | medium | | | 0 | | [tau3-banking_knowledge-task-085](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-085.md) | medium | | | 0 | | [tau3-banking_knowledge-task-086](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-086.md) | medium | | | 0 | | [tau3-banking_knowledge-task-087](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-087.md) | medium | | | 0 | | [tau3-banking_knowledge-task-088](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-088.md) | medium | | | 0 | | [tau3-banking_knowledge-task-089](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-089.md) | medium | | | 0 | | [tau3-banking_knowledge-task-090](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-090.md) | medium | | | 0 | | [tau3-banking_knowledge-task-091](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-091.md) | medium | | | 0 | | [tau3-banking_knowledge-task-092](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-092.md) | medium | | | 0 | | [tau3-banking_knowledge-task-093](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-093.md) | medium | | | 0 | | [tau3-banking_knowledge-task-094](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-094.md) | medium | | | 0 | | [tau3-banking_knowledge-task-095](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-095.md) | medium | | | 0 | | [tau3-banking_knowledge-task-096](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-096.md) | medium | | | 0 | | [tau3-banking_knowledge-task-097](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-097.md) | medium | | | 0 | | [tau3-banking_knowledge-task-098](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-098.md) | medium | | | 0 | | [tau3-banking_knowledge-task-099](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-099.md) | medium | | | 0 | | [tau3-banking_knowledge-task-100](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-100.md) | medium | | | 0 | | [tau3-banking_knowledge-task-101](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-101.md) | medium | | | 0 | | [tau3-banking_knowledge-task-102](https://harnessreport.com/tasks/tau3-bench/tau3-banking_knowledge-task-102.md) | medium | | | 0 | | [tau3-retail-0](https://harnessreport.com/tasks/tau3-bench/tau3-retail-0.md) | medium | | | 0 | | [tau3-retail-1](https://harnessreport.com/tasks/tau3-bench/tau3-retail-1.md) | medium | | | 0 | | [tau3-retail-10](https://harnessreport.com/tasks/tau3-bench/tau3-retail-10.md) | medium | | | 0 | | [tau3-retail-100](https://harnessreport.com/tasks/tau3-bench/tau3-retail-100.md) | medium | | | 0 | | [tau3-retail-101](https://harnessreport.com/tasks/tau3-bench/tau3-retail-101.md) | medium | | | 0 | | [tau3-retail-102](https://harnessreport.com/tasks/tau3-bench/tau3-retail-102.md) | medium | | | 0 | | [tau3-retail-103](https://harnessreport.com/tasks/tau3-bench/tau3-retail-103.md) | medium | | | 0 | | [tau3-retail-104](https://harnessreport.com/tasks/tau3-bench/tau3-retail-104.md) | medium | | | 0 | | [tau3-retail-105](https://harnessreport.com/tasks/tau3-bench/tau3-retail-105.md) | medium | | | 0 | | [tau3-retail-106](https://harnessreport.com/tasks/tau3-bench/tau3-retail-106.md) | medium | | | 0 | | [tau3-retail-107](https://harnessreport.com/tasks/tau3-bench/tau3-retail-107.md) | medium | | | 0 | | [tau3-retail-108](https://harnessreport.com/tasks/tau3-bench/tau3-retail-108.md) | medium | | | 0 | | [tau3-retail-109](https://harnessreport.com/tasks/tau3-bench/tau3-retail-109.md) | medium | | | 0 | | [tau3-retail-11](https://harnessreport.com/tasks/tau3-bench/tau3-retail-11.md) | medium | | | 0 | | [tau3-retail-110](https://harnessreport.com/tasks/tau3-bench/tau3-retail-110.md) | medium | | | 0 | | [tau3-retail-111](https://harnessreport.com/tasks/tau3-bench/tau3-retail-111.md) | medium | | | 0 | | [tau3-retail-112](https://harnessreport.com/tasks/tau3-bench/tau3-retail-112.md) | medium | | | 0 | | [tau3-retail-113](https://harnessreport.com/tasks/tau3-bench/tau3-retail-113.md) | medium | | | 0 | | [tau3-retail-12](https://harnessreport.com/tasks/tau3-bench/tau3-retail-12.md) | medium | | | 0 | | [tau3-retail-13](https://harnessreport.com/tasks/tau3-bench/tau3-retail-13.md) | medium | | | 0 | | [tau3-retail-14](https://harnessreport.com/tasks/tau3-bench/tau3-retail-14.md) | medium | | | 0 | | [tau3-retail-15](https://harnessreport.com/tasks/tau3-bench/tau3-retail-15.md) | medium | | | 0 | | [tau3-retail-16](https://harnessreport.com/tasks/tau3-bench/tau3-retail-16.md) | medium | | | 0 | | [tau3-retail-17](https://harnessreport.com/tasks/tau3-bench/tau3-retail-17.md) | medium | | | 0 | | [tau3-retail-18](https://harnessreport.com/tasks/tau3-bench/tau3-retail-18.md) | medium | | | 0 | | [tau3-retail-19](https://harnessreport.com/tasks/tau3-bench/tau3-retail-19.md) | medium | | | 0 | | [tau3-retail-2](https://harnessreport.com/tasks/tau3-bench/tau3-retail-2.md) | medium | | | 0 | | [tau3-retail-20](https://harnessreport.com/tasks/tau3-bench/tau3-retail-20.md) | medium | | | 0 | | [tau3-retail-21](https://harnessreport.com/tasks/tau3-bench/tau3-retail-21.md) | medium | | | 0 | | [tau3-retail-22](https://harnessreport.com/tasks/tau3-bench/tau3-retail-22.md) | medium | | | 0 | | [tau3-retail-23](https://harnessreport.com/tasks/tau3-bench/tau3-retail-23.md) | medium | | | 0 | | [tau3-retail-24](https://harnessreport.com/tasks/tau3-bench/tau3-retail-24.md) | medium | | | 0 | | [tau3-retail-25](https://harnessreport.com/tasks/tau3-bench/tau3-retail-25.md) | medium | | | 0 | | [tau3-retail-26](https://harnessreport.com/tasks/tau3-bench/tau3-retail-26.md) | medium | | | 0 | | [tau3-retail-27](https://harnessreport.com/tasks/tau3-bench/tau3-retail-27.md) | medium | | | 0 | | [tau3-retail-28](https://harnessreport.com/tasks/tau3-bench/tau3-retail-28.md) | medium | | | 0 | | [tau3-retail-29](https://harnessreport.com/tasks/tau3-bench/tau3-retail-29.md) | medium | | | 0 | | [tau3-retail-3](https://harnessreport.com/tasks/tau3-bench/tau3-retail-3.md) | medium | | | 0 | | [tau3-retail-30](https://harnessreport.com/tasks/tau3-bench/tau3-retail-30.md) | medium | | | 0 | | [tau3-retail-31](https://harnessreport.com/tasks/tau3-bench/tau3-retail-31.md) | medium | | | 0 | | [tau3-retail-32](https://harnessreport.com/tasks/tau3-bench/tau3-retail-32.md) | medium | | | 0 | | [tau3-retail-33](https://harnessreport.com/tasks/tau3-bench/tau3-retail-33.md) | medium | | | 0 | | [tau3-retail-34](https://harnessreport.com/tasks/tau3-bench/tau3-retail-34.md) | medium | | | 0 | | [tau3-retail-35](https://harnessreport.com/tasks/tau3-bench/tau3-retail-35.md) | medium | | | 0 | | [tau3-retail-36](https://harnessreport.com/tasks/tau3-bench/tau3-retail-36.md) | medium | | | 0 | | [tau3-retail-37](https://harnessreport.com/tasks/tau3-bench/tau3-retail-37.md) | medium | | | 0 | | [tau3-retail-38](https://harnessreport.com/tasks/tau3-bench/tau3-retail-38.md) | medium | | | 0 | | [tau3-retail-39](https://harnessreport.com/tasks/tau3-bench/tau3-retail-39.md) | medium | | | 0 | | [tau3-retail-4](https://harnessreport.com/tasks/tau3-bench/tau3-retail-4.md) | medium | | | 0 | | [tau3-retail-40](https://harnessreport.com/tasks/tau3-bench/tau3-retail-40.md) | medium | | | 0 | | [tau3-retail-41](https://harnessreport.com/tasks/tau3-bench/tau3-retail-41.md) | medium | | | 0 | | [tau3-retail-42](https://harnessreport.com/tasks/tau3-bench/tau3-retail-42.md) | medium | | | 0 | | [tau3-retail-43](https://harnessreport.com/tasks/tau3-bench/tau3-retail-43.md) | medium | | | 0 | More: https://harnessreport.com/tasks/tau3-bench.md?after=tau3-retail-43 --- Harness Report runs agent harnesses from their GitHub repos on Harbor tasks and records every model call. Every page is also `.md` and `.json`; index: https://harnessreport.com/llms.txt · MCP: https://harnessreport.com/mcp