# medagentbench - domain: healthcare - n_tasks: 300 - n_runnable: 0 - owner_org: Stanford - grading: state-check - task_kind: FHIR EHR tasks in a virtual EHR environment - url_repo: https://github.com/stanfordmlgroup/MedAgentBench ## Tasks | task | difficulty | language | runnable | harnesses tried | |---|---|---|---|---| | [task10_1](https://harnessreport.com/tasks/medagentbench/task10_1.md) | hard | | | 0 | | [task10_10](https://harnessreport.com/tasks/medagentbench/task10_10.md) | hard | | | 0 | | [task10_11](https://harnessreport.com/tasks/medagentbench/task10_11.md) | hard | | | 0 | | [task10_12](https://harnessreport.com/tasks/medagentbench/task10_12.md) | hard | | | 0 | | [task10_13](https://harnessreport.com/tasks/medagentbench/task10_13.md) | hard | | | 0 | | [task10_14](https://harnessreport.com/tasks/medagentbench/task10_14.md) | hard | | | 0 | | [task10_15](https://harnessreport.com/tasks/medagentbench/task10_15.md) | hard | | | 0 | | [task10_16](https://harnessreport.com/tasks/medagentbench/task10_16.md) | hard | | | 0 | | [task10_17](https://harnessreport.com/tasks/medagentbench/task10_17.md) | hard | | | 0 | | [task10_18](https://harnessreport.com/tasks/medagentbench/task10_18.md) | hard | | | 0 | | [task10_19](https://harnessreport.com/tasks/medagentbench/task10_19.md) | hard | | | 0 | | [task10_2](https://harnessreport.com/tasks/medagentbench/task10_2.md) | hard | | | 0 | | [task10_20](https://harnessreport.com/tasks/medagentbench/task10_20.md) | hard | | | 0 | | [task10_21](https://harnessreport.com/tasks/medagentbench/task10_21.md) | hard | | | 0 | | [task10_22](https://harnessreport.com/tasks/medagentbench/task10_22.md) | hard | | | 0 | | [task10_23](https://harnessreport.com/tasks/medagentbench/task10_23.md) | hard | | | 0 | | [task10_24](https://harnessreport.com/tasks/medagentbench/task10_24.md) | hard | | | 0 | | [task10_25](https://harnessreport.com/tasks/medagentbench/task10_25.md) | hard | | | 0 | | [task10_26](https://harnessreport.com/tasks/medagentbench/task10_26.md) | hard | | | 0 | | [task10_27](https://harnessreport.com/tasks/medagentbench/task10_27.md) | hard | | | 0 | | [task10_28](https://harnessreport.com/tasks/medagentbench/task10_28.md) | hard | | | 0 | | [task10_29](https://harnessreport.com/tasks/medagentbench/task10_29.md) | hard | | | 0 | | [task10_3](https://harnessreport.com/tasks/medagentbench/task10_3.md) | hard | | | 0 | | [task10_30](https://harnessreport.com/tasks/medagentbench/task10_30.md) | hard | | | 0 | | [task10_4](https://harnessreport.com/tasks/medagentbench/task10_4.md) | hard | | | 0 | | [task10_5](https://harnessreport.com/tasks/medagentbench/task10_5.md) | hard | | | 0 | | [task10_6](https://harnessreport.com/tasks/medagentbench/task10_6.md) | hard | | | 0 | | [task10_7](https://harnessreport.com/tasks/medagentbench/task10_7.md) | hard | | | 0 | | [task10_8](https://harnessreport.com/tasks/medagentbench/task10_8.md) | hard | | | 0 | | [task10_9](https://harnessreport.com/tasks/medagentbench/task10_9.md) | hard | | | 0 | | [task1_1](https://harnessreport.com/tasks/medagentbench/task1_1.md) | hard | | | 0 | | [task1_10](https://harnessreport.com/tasks/medagentbench/task1_10.md) | hard | | | 0 | | [task1_11](https://harnessreport.com/tasks/medagentbench/task1_11.md) | hard | | | 0 | | [task1_12](https://harnessreport.com/tasks/medagentbench/task1_12.md) | hard | | | 0 | | [task1_13](https://harnessreport.com/tasks/medagentbench/task1_13.md) | hard | | | 0 | | [task1_14](https://harnessreport.com/tasks/medagentbench/task1_14.md) | hard | | | 0 | | [task1_15](https://harnessreport.com/tasks/medagentbench/task1_15.md) | hard | | | 0 | | [task1_16](https://harnessreport.com/tasks/medagentbench/task1_16.md) | hard | | | 0 | | [task1_17](https://harnessreport.com/tasks/medagentbench/task1_17.md) | hard | | | 0 | | [task1_18](https://harnessreport.com/tasks/medagentbench/task1_18.md) | hard | | | 0 | | [task1_19](https://harnessreport.com/tasks/medagentbench/task1_19.md) | hard | | | 0 | | [task1_2](https://harnessreport.com/tasks/medagentbench/task1_2.md) | hard | | | 0 | | [task1_20](https://harnessreport.com/tasks/medagentbench/task1_20.md) | hard | | | 0 | | [task1_21](https://harnessreport.com/tasks/medagentbench/task1_21.md) | hard | | | 0 | | [task1_22](https://harnessreport.com/tasks/medagentbench/task1_22.md) | hard | | | 0 | | [task1_23](https://harnessreport.com/tasks/medagentbench/task1_23.md) | hard | | | 0 | | [task1_24](https://harnessreport.com/tasks/medagentbench/task1_24.md) | hard | | | 0 | | [task1_25](https://harnessreport.com/tasks/medagentbench/task1_25.md) | hard | | | 0 | | [task1_26](https://harnessreport.com/tasks/medagentbench/task1_26.md) | hard | | | 0 | | [task1_27](https://harnessreport.com/tasks/medagentbench/task1_27.md) | hard | | | 0 | | [task1_28](https://harnessreport.com/tasks/medagentbench/task1_28.md) | hard | | | 0 | | [task1_29](https://harnessreport.com/tasks/medagentbench/task1_29.md) | hard | | | 0 | | [task1_3](https://harnessreport.com/tasks/medagentbench/task1_3.md) | hard | | | 0 | | [task1_30](https://harnessreport.com/tasks/medagentbench/task1_30.md) | hard | | | 0 | | [task1_4](https://harnessreport.com/tasks/medagentbench/task1_4.md) | hard | | | 0 | | [task1_5](https://harnessreport.com/tasks/medagentbench/task1_5.md) | hard | | | 0 | | [task1_6](https://harnessreport.com/tasks/medagentbench/task1_6.md) | hard | | | 0 | | [task1_7](https://harnessreport.com/tasks/medagentbench/task1_7.md) | hard | | | 0 | | [task1_8](https://harnessreport.com/tasks/medagentbench/task1_8.md) | hard | | | 0 | | [task1_9](https://harnessreport.com/tasks/medagentbench/task1_9.md) | hard | | | 0 | | [task2_1](https://harnessreport.com/tasks/medagentbench/task2_1.md) | hard | | | 0 | | [task2_10](https://harnessreport.com/tasks/medagentbench/task2_10.md) | hard | | | 0 | | [task2_11](https://harnessreport.com/tasks/medagentbench/task2_11.md) | hard | | | 0 | | [task2_12](https://harnessreport.com/tasks/medagentbench/task2_12.md) | hard | | | 0 | | [task2_13](https://harnessreport.com/tasks/medagentbench/task2_13.md) | hard | | | 0 | | [task2_14](https://harnessreport.com/tasks/medagentbench/task2_14.md) | hard | | | 0 | | [task2_15](https://harnessreport.com/tasks/medagentbench/task2_15.md) | hard | | | 0 | | [task2_16](https://harnessreport.com/tasks/medagentbench/task2_16.md) | hard | | | 0 | | [task2_17](https://harnessreport.com/tasks/medagentbench/task2_17.md) | hard | | | 0 | | [task2_18](https://harnessreport.com/tasks/medagentbench/task2_18.md) | hard | | | 0 | | [task2_19](https://harnessreport.com/tasks/medagentbench/task2_19.md) | hard | | | 0 | | [task2_2](https://harnessreport.com/tasks/medagentbench/task2_2.md) | hard | | | 0 | | [task2_20](https://harnessreport.com/tasks/medagentbench/task2_20.md) | hard | | | 0 | | [task2_21](https://harnessreport.com/tasks/medagentbench/task2_21.md) | hard | | | 0 | | [task2_22](https://harnessreport.com/tasks/medagentbench/task2_22.md) | hard | | | 0 | | [task2_23](https://harnessreport.com/tasks/medagentbench/task2_23.md) | hard | | | 0 | | [task2_24](https://harnessreport.com/tasks/medagentbench/task2_24.md) | hard | | | 0 | | [task2_25](https://harnessreport.com/tasks/medagentbench/task2_25.md) | hard | | | 0 | | [task2_26](https://harnessreport.com/tasks/medagentbench/task2_26.md) | hard | | | 0 | | [task2_27](https://harnessreport.com/tasks/medagentbench/task2_27.md) | hard | | | 0 | | [task2_28](https://harnessreport.com/tasks/medagentbench/task2_28.md) | hard | | | 0 | | [task2_29](https://harnessreport.com/tasks/medagentbench/task2_29.md) | hard | | | 0 | | [task2_3](https://harnessreport.com/tasks/medagentbench/task2_3.md) | hard | | | 0 | | [task2_30](https://harnessreport.com/tasks/medagentbench/task2_30.md) | hard | | | 0 | | [task2_4](https://harnessreport.com/tasks/medagentbench/task2_4.md) | hard | | | 0 | | [task2_5](https://harnessreport.com/tasks/medagentbench/task2_5.md) | hard | | | 0 | | [task2_6](https://harnessreport.com/tasks/medagentbench/task2_6.md) | hard | | | 0 | | [task2_7](https://harnessreport.com/tasks/medagentbench/task2_7.md) | hard | | | 0 | | [task2_8](https://harnessreport.com/tasks/medagentbench/task2_8.md) | hard | | | 0 | | [task2_9](https://harnessreport.com/tasks/medagentbench/task2_9.md) | hard | | | 0 | | [task3_1](https://harnessreport.com/tasks/medagentbench/task3_1.md) | hard | | | 0 | | [task3_10](https://harnessreport.com/tasks/medagentbench/task3_10.md) | hard | | | 0 | | [task3_11](https://harnessreport.com/tasks/medagentbench/task3_11.md) | hard | | | 0 | | [task3_12](https://harnessreport.com/tasks/medagentbench/task3_12.md) | hard | | | 0 | | [task3_13](https://harnessreport.com/tasks/medagentbench/task3_13.md) | hard | | | 0 | | [task3_14](https://harnessreport.com/tasks/medagentbench/task3_14.md) | hard | | | 0 | | [task3_15](https://harnessreport.com/tasks/medagentbench/task3_15.md) | hard | | | 0 | | [task3_16](https://harnessreport.com/tasks/medagentbench/task3_16.md) | hard | | | 0 | | [task3_17](https://harnessreport.com/tasks/medagentbench/task3_17.md) | hard | | | 0 | | [task3_18](https://harnessreport.com/tasks/medagentbench/task3_18.md) | hard | | | 0 | | [task3_19](https://harnessreport.com/tasks/medagentbench/task3_19.md) | hard | | | 0 | | [task3_2](https://harnessreport.com/tasks/medagentbench/task3_2.md) | hard | | | 0 | | [task3_20](https://harnessreport.com/tasks/medagentbench/task3_20.md) | hard | | | 0 | | [task3_21](https://harnessreport.com/tasks/medagentbench/task3_21.md) | hard | | | 0 | | [task3_22](https://harnessreport.com/tasks/medagentbench/task3_22.md) | hard | | | 0 | | [task3_23](https://harnessreport.com/tasks/medagentbench/task3_23.md) | hard | | | 0 | | [task3_24](https://harnessreport.com/tasks/medagentbench/task3_24.md) | hard | | | 0 | | [task3_25](https://harnessreport.com/tasks/medagentbench/task3_25.md) | hard | | | 0 | | [task3_26](https://harnessreport.com/tasks/medagentbench/task3_26.md) | hard | | | 0 | | [task3_27](https://harnessreport.com/tasks/medagentbench/task3_27.md) | hard | | | 0 | | [task3_28](https://harnessreport.com/tasks/medagentbench/task3_28.md) | hard | | | 0 | | [task3_29](https://harnessreport.com/tasks/medagentbench/task3_29.md) | hard | | | 0 | | [task3_3](https://harnessreport.com/tasks/medagentbench/task3_3.md) | hard | | | 0 | | [task3_30](https://harnessreport.com/tasks/medagentbench/task3_30.md) | hard | | | 0 | | [task3_4](https://harnessreport.com/tasks/medagentbench/task3_4.md) | hard | | | 0 | | [task3_5](https://harnessreport.com/tasks/medagentbench/task3_5.md) | hard | | | 0 | | [task3_6](https://harnessreport.com/tasks/medagentbench/task3_6.md) | hard | | | 0 | | [task3_7](https://harnessreport.com/tasks/medagentbench/task3_7.md) | hard | | | 0 | | [task3_8](https://harnessreport.com/tasks/medagentbench/task3_8.md) | hard | | | 0 | | [task3_9](https://harnessreport.com/tasks/medagentbench/task3_9.md) | hard | | | 0 | | [task4_1](https://harnessreport.com/tasks/medagentbench/task4_1.md) | hard | | | 0 | | [task4_10](https://harnessreport.com/tasks/medagentbench/task4_10.md) | hard | | | 0 | | [task4_11](https://harnessreport.com/tasks/medagentbench/task4_11.md) | hard | | | 0 | | [task4_12](https://harnessreport.com/tasks/medagentbench/task4_12.md) | hard | | | 0 | | [task4_13](https://harnessreport.com/tasks/medagentbench/task4_13.md) | hard | | | 0 | | [task4_14](https://harnessreport.com/tasks/medagentbench/task4_14.md) | hard | | | 0 | | [task4_15](https://harnessreport.com/tasks/medagentbench/task4_15.md) | hard | | | 0 | | [task4_16](https://harnessreport.com/tasks/medagentbench/task4_16.md) | hard | | | 0 | | [task4_17](https://harnessreport.com/tasks/medagentbench/task4_17.md) | hard | | | 0 | | [task4_18](https://harnessreport.com/tasks/medagentbench/task4_18.md) | hard | | | 0 | | [task4_19](https://harnessreport.com/tasks/medagentbench/task4_19.md) | hard | | | 0 | | [task4_2](https://harnessreport.com/tasks/medagentbench/task4_2.md) | hard | | | 0 | | [task4_20](https://harnessreport.com/tasks/medagentbench/task4_20.md) | hard | | | 0 | | [task4_21](https://harnessreport.com/tasks/medagentbench/task4_21.md) | hard | | | 0 | | [task4_22](https://harnessreport.com/tasks/medagentbench/task4_22.md) | hard | | | 0 | | [task4_23](https://harnessreport.com/tasks/medagentbench/task4_23.md) | hard | | | 0 | | [task4_24](https://harnessreport.com/tasks/medagentbench/task4_24.md) | hard | | | 0 | | [task4_25](https://harnessreport.com/tasks/medagentbench/task4_25.md) | hard | | | 0 | | [task4_26](https://harnessreport.com/tasks/medagentbench/task4_26.md) | hard | | | 0 | | [task4_27](https://harnessreport.com/tasks/medagentbench/task4_27.md) | hard | | | 0 | | [task4_28](https://harnessreport.com/tasks/medagentbench/task4_28.md) | hard | | | 0 | | [task4_29](https://harnessreport.com/tasks/medagentbench/task4_29.md) | hard | | | 0 | | [task4_3](https://harnessreport.com/tasks/medagentbench/task4_3.md) | hard | | | 0 | | [task4_30](https://harnessreport.com/tasks/medagentbench/task4_30.md) | hard | | | 0 | | [task4_4](https://harnessreport.com/tasks/medagentbench/task4_4.md) | hard | | | 0 | | [task4_5](https://harnessreport.com/tasks/medagentbench/task4_5.md) | hard | | | 0 | | [task4_6](https://harnessreport.com/tasks/medagentbench/task4_6.md) | hard | | | 0 | | [task4_7](https://harnessreport.com/tasks/medagentbench/task4_7.md) | hard | | | 0 | | [task4_8](https://harnessreport.com/tasks/medagentbench/task4_8.md) | hard | | | 0 | | [task4_9](https://harnessreport.com/tasks/medagentbench/task4_9.md) | hard | | | 0 | | [task5_1](https://harnessreport.com/tasks/medagentbench/task5_1.md) | hard | | | 0 | | [task5_10](https://harnessreport.com/tasks/medagentbench/task5_10.md) | hard | | | 0 | | [task5_11](https://harnessreport.com/tasks/medagentbench/task5_11.md) | hard | | | 0 | | [task5_12](https://harnessreport.com/tasks/medagentbench/task5_12.md) | hard | | | 0 | | [task5_13](https://harnessreport.com/tasks/medagentbench/task5_13.md) | hard | | | 0 | | [task5_14](https://harnessreport.com/tasks/medagentbench/task5_14.md) | hard | | | 0 | | [task5_15](https://harnessreport.com/tasks/medagentbench/task5_15.md) | hard | | | 0 | | [task5_16](https://harnessreport.com/tasks/medagentbench/task5_16.md) | hard | | | 0 | | [task5_17](https://harnessreport.com/tasks/medagentbench/task5_17.md) | hard | | | 0 | | [task5_18](https://harnessreport.com/tasks/medagentbench/task5_18.md) | hard | | | 0 | | [task5_19](https://harnessreport.com/tasks/medagentbench/task5_19.md) | hard | | | 0 | | [task5_2](https://harnessreport.com/tasks/medagentbench/task5_2.md) | hard | | | 0 | | [task5_20](https://harnessreport.com/tasks/medagentbench/task5_20.md) | hard | | | 0 | | [task5_21](https://harnessreport.com/tasks/medagentbench/task5_21.md) | hard | | | 0 | | [task5_22](https://harnessreport.com/tasks/medagentbench/task5_22.md) | hard | | | 0 | | [task5_23](https://harnessreport.com/tasks/medagentbench/task5_23.md) | hard | | | 0 | | [task5_24](https://harnessreport.com/tasks/medagentbench/task5_24.md) | hard | | | 0 | | [task5_25](https://harnessreport.com/tasks/medagentbench/task5_25.md) | hard | | | 0 | | [task5_26](https://harnessreport.com/tasks/medagentbench/task5_26.md) | hard | | | 0 | | [task5_27](https://harnessreport.com/tasks/medagentbench/task5_27.md) | hard | | | 0 | | [task5_28](https://harnessreport.com/tasks/medagentbench/task5_28.md) | hard | | | 0 | | [task5_29](https://harnessreport.com/tasks/medagentbench/task5_29.md) | hard | | | 0 | | [task5_3](https://harnessreport.com/tasks/medagentbench/task5_3.md) | hard | | | 0 | | [task5_30](https://harnessreport.com/tasks/medagentbench/task5_30.md) | hard | | | 0 | | [task5_4](https://harnessreport.com/tasks/medagentbench/task5_4.md) | hard | | | 0 | | [task5_5](https://harnessreport.com/tasks/medagentbench/task5_5.md) | hard | | | 0 | | [task5_6](https://harnessreport.com/tasks/medagentbench/task5_6.md) | hard | | | 0 | | [task5_7](https://harnessreport.com/tasks/medagentbench/task5_7.md) | hard | | | 0 | | [task5_8](https://harnessreport.com/tasks/medagentbench/task5_8.md) | hard | | | 0 | | [task5_9](https://harnessreport.com/tasks/medagentbench/task5_9.md) | hard | | | 0 | | [task6_1](https://harnessreport.com/tasks/medagentbench/task6_1.md) | hard | | | 0 | | [task6_10](https://harnessreport.com/tasks/medagentbench/task6_10.md) | hard | | | 0 | | [task6_11](https://harnessreport.com/tasks/medagentbench/task6_11.md) | hard | | | 0 | | [task6_12](https://harnessreport.com/tasks/medagentbench/task6_12.md) | hard | | | 0 | | [task6_13](https://harnessreport.com/tasks/medagentbench/task6_13.md) | hard | | | 0 | | [task6_14](https://harnessreport.com/tasks/medagentbench/task6_14.md) | hard | | | 0 | | [task6_15](https://harnessreport.com/tasks/medagentbench/task6_15.md) | hard | | | 0 | | [task6_16](https://harnessreport.com/tasks/medagentbench/task6_16.md) | hard | | | 0 | | [task6_17](https://harnessreport.com/tasks/medagentbench/task6_17.md) | hard | | | 0 | | [task6_18](https://harnessreport.com/tasks/medagentbench/task6_18.md) | hard | | | 0 | | [task6_19](https://harnessreport.com/tasks/medagentbench/task6_19.md) | hard | | | 0 | | [task6_2](https://harnessreport.com/tasks/medagentbench/task6_2.md) | hard | | | 0 | | [task6_20](https://harnessreport.com/tasks/medagentbench/task6_20.md) | hard | | | 0 | | [task6_21](https://harnessreport.com/tasks/medagentbench/task6_21.md) | hard | | | 0 | | [task6_22](https://harnessreport.com/tasks/medagentbench/task6_22.md) | hard | | | 0 | | [task6_23](https://harnessreport.com/tasks/medagentbench/task6_23.md) | hard | | | 0 | | [task6_24](https://harnessreport.com/tasks/medagentbench/task6_24.md) | hard | | | 0 | | [task6_25](https://harnessreport.com/tasks/medagentbench/task6_25.md) | hard | | | 0 | | [task6_26](https://harnessreport.com/tasks/medagentbench/task6_26.md) | hard | | | 0 | | [task6_27](https://harnessreport.com/tasks/medagentbench/task6_27.md) | hard | | | 0 | More: https://harnessreport.com/tasks/medagentbench.md?after=task6_27 --- 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