bfcl

v1.0

Berkeley Function-Calling Leaderboard: 3,641 function calling tasks for evaluating LLM tool use capabilities across simple, multiple, parallel, and irrelevance categories.

uvx harbor run -d bfcl@1.0

Tasks (3641)

bfcl-live-irrelevance-693-225-3
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-693-225-3
6bedd78
bfcl-live-irrelevance-694-225-4
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-694-225-4
6bedd78
bfcl-live-irrelevance-695-225-5
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-695-225-5
6bedd78
bfcl-live-irrelevance-696-226-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-696-226-0
6bedd78
bfcl-live-irrelevance-697-227-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-697-227-0
6bedd78
bfcl-live-irrelevance-698-227-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-698-227-1
6bedd78
bfcl-live-irrelevance-699-228-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-699-228-0
6bedd78
bfcl-live-irrelevance-7-0-7
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-7-0-7
6bedd78
bfcl-live-irrelevance-70-2-58
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-70-2-58
6bedd78
bfcl-live-irrelevance-700-229-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-700-229-0
6bedd78
bfcl-live-irrelevance-701-230-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-701-230-0
6bedd78
bfcl-live-irrelevance-702-230-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-702-230-1
6bedd78
bfcl-live-irrelevance-703-230-2
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-703-230-2
6bedd78
bfcl-live-irrelevance-704-230-3
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-704-230-3
6bedd78
bfcl-live-irrelevance-705-231-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-705-231-0
6bedd78
bfcl-live-irrelevance-706-231-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-706-231-1
6bedd78
bfcl-live-irrelevance-707-231-2
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-707-231-2
6bedd78
bfcl-live-irrelevance-708-232-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-708-232-0
6bedd78
bfcl-live-irrelevance-709-233-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-709-233-0
6bedd78
bfcl-live-irrelevance-71-2-59
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-71-2-59
6bedd78
bfcl-live-irrelevance-710-234-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-710-234-0
6bedd78
bfcl-live-irrelevance-711-235-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-711-235-0
6bedd78
bfcl-live-irrelevance-712-236-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-712-236-0
6bedd78
bfcl-live-irrelevance-713-237-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-713-237-0
6bedd78
bfcl-live-irrelevance-714-237-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-714-237-1
6bedd78
bfcl-live-irrelevance-715-237-2
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-715-237-2
6bedd78
bfcl-live-irrelevance-716-237-3
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-716-237-3
6bedd78
bfcl-live-irrelevance-717-237-4
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-717-237-4
6bedd78
bfcl-live-irrelevance-718-237-5
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-718-237-5
6bedd78
bfcl-live-irrelevance-719-238-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-719-238-0
6bedd78
bfcl-live-irrelevance-72-2-60
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-72-2-60
6bedd78
bfcl-live-irrelevance-720-238-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-720-238-1
6bedd78
bfcl-live-irrelevance-721-239-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-721-239-0
6bedd78
bfcl-live-irrelevance-722-240-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-722-240-0
6bedd78
bfcl-live-irrelevance-723-240-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-723-240-1
6bedd78
bfcl-live-irrelevance-724-241-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-724-241-0
6bedd78
bfcl-live-irrelevance-725-241-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-725-241-1
6bedd78
bfcl-live-irrelevance-726-242-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-726-242-0
6bedd78
bfcl-live-irrelevance-727-243-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-727-243-0
6bedd78
bfcl-live-irrelevance-728-244-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-728-244-0
6bedd78
bfcl-live-irrelevance-729-244-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-729-244-1
6bedd78
bfcl-live-irrelevance-73-2-61
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-73-2-61
6bedd78
bfcl-live-irrelevance-730-245-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-730-245-0
6bedd78
bfcl-live-irrelevance-731-246-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-731-246-0
6bedd78
bfcl-live-irrelevance-732-247-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-732-247-0
6bedd78
bfcl-live-irrelevance-733-248-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-733-248-0
6bedd78
bfcl-live-irrelevance-734-249-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-734-249-0
6bedd78
bfcl-live-irrelevance-735-249-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-735-249-1
6bedd78
bfcl-live-irrelevance-736-250-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-736-250-0
6bedd78
bfcl-live-irrelevance-737-251-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-737-251-0
6bedd78
bfcl-live-irrelevance-738-252-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-738-252-0
6bedd78
bfcl-live-irrelevance-739-253-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-739-253-0
6bedd78
bfcl-live-irrelevance-74-2-62
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-74-2-62
6bedd78
bfcl-live-irrelevance-740-254-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-740-254-0
6bedd78
bfcl-live-irrelevance-741-254-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-741-254-1
6bedd78
bfcl-live-irrelevance-742-254-2
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-742-254-2
6bedd78
bfcl-live-irrelevance-743-254-3
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-743-254-3
6bedd78
bfcl-live-irrelevance-744-255-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-744-255-0
6bedd78
bfcl-live-irrelevance-745-256-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-745-256-0
6bedd78
bfcl-live-irrelevance-746-257-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-746-257-0
6bedd78
bfcl-live-irrelevance-747-258-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-747-258-0
6bedd78
bfcl-live-irrelevance-748-259-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-748-259-0
6bedd78
bfcl-live-irrelevance-749-260-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-749-260-0
6bedd78
bfcl-live-irrelevance-75-2-63
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-75-2-63
6bedd78
bfcl-live-irrelevance-750-261-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-750-261-0
6bedd78
bfcl-live-irrelevance-751-262-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-751-262-0
6bedd78
bfcl-live-irrelevance-752-263-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-752-263-0
6bedd78
bfcl-live-irrelevance-753-264-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-753-264-0
6bedd78
bfcl-live-irrelevance-754-265-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-754-265-0
6bedd78
bfcl-live-irrelevance-755-266-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-755-266-0
6bedd78
bfcl-live-irrelevance-756-267-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-756-267-0
6bedd78
bfcl-live-irrelevance-757-268-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-757-268-0
6bedd78
bfcl-live-irrelevance-758-269-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-758-269-0
6bedd78
bfcl-live-irrelevance-759-270-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-759-270-0
6bedd78
bfcl-live-irrelevance-76-2-64
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-76-2-64
6bedd78
bfcl-live-irrelevance-760-271-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-760-271-0
6bedd78
bfcl-live-irrelevance-761-272-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-761-272-0
6bedd78
bfcl-live-irrelevance-762-272-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-762-272-1
6bedd78
bfcl-live-irrelevance-763-273-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-763-273-0
6bedd78
bfcl-live-irrelevance-764-274-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-764-274-0
6bedd78
bfcl-live-irrelevance-765-274-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-765-274-1
6bedd78
bfcl-live-irrelevance-766-275-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-766-275-0
6bedd78
bfcl-live-irrelevance-767-276-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-767-276-0
6bedd78
bfcl-live-irrelevance-768-277-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-768-277-0
6bedd78
bfcl-live-irrelevance-769-278-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-769-278-0
6bedd78
bfcl-live-irrelevance-77-2-65
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-77-2-65
6bedd78
bfcl-live-irrelevance-770-279-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-770-279-0
6bedd78
bfcl-live-irrelevance-771-280-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-771-280-0
6bedd78
bfcl-live-irrelevance-772-281-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-772-281-0
6bedd78
bfcl-live-irrelevance-773-282-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-773-282-0
6bedd78
bfcl-live-irrelevance-774-283-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-774-283-0
6bedd78
bfcl-live-irrelevance-775-284-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-775-284-0
6bedd78
bfcl-live-irrelevance-776-285-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-776-285-0
6bedd78
bfcl-live-irrelevance-777-286-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-777-286-0
6bedd78
bfcl-live-irrelevance-778-287-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-778-287-0
6bedd78
bfcl-live-irrelevance-779-288-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-779-288-0
6bedd78
bfcl-live-irrelevance-78-2-66
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-78-2-66
6bedd78
bfcl-live-irrelevance-780-289-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-780-289-0
6bedd78
bfcl-live-irrelevance-781-290-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-781-290-0
6bedd78
bfcl-live-irrelevance-782-291-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-782-291-0
6bedd78