bfcl
v1.0Berkeley 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@1.0Tasks (3641)
bfcl-live-irrelevance-873-358-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-873-358-06bedd78
bfcl-live-irrelevance-874-359-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-874-359-06bedd78
bfcl-live-irrelevance-875-360-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-875-360-06bedd78
bfcl-live-irrelevance-876-361-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-876-361-06bedd78
bfcl-live-irrelevance-877-362-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-877-362-06bedd78
bfcl-live-irrelevance-878-363-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-878-363-06bedd78
bfcl-live-irrelevance-879-364-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-879-364-06bedd78
bfcl-live-irrelevance-88-2-76
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-88-2-766bedd78
bfcl-live-irrelevance-880-365-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-880-365-06bedd78
bfcl-live-irrelevance-881-366-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-881-366-06bedd78
bfcl-live-irrelevance-882-882-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-882-882-06bedd78
bfcl-live-irrelevance-883-883-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-883-883-06bedd78
bfcl-live-irrelevance-89-2-77
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-89-2-776bedd78
bfcl-live-irrelevance-9-0-9
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-9-0-96bedd78
bfcl-live-irrelevance-90-2-78
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-90-2-786bedd78
bfcl-live-irrelevance-91-2-79
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-91-2-796bedd78
bfcl-live-irrelevance-92-2-80
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-92-2-806bedd78
bfcl-live-irrelevance-93-2-81
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-93-2-816bedd78
bfcl-live-irrelevance-94-2-82
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-94-2-826bedd78
bfcl-live-irrelevance-95-2-83
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-95-2-836bedd78
bfcl-live-irrelevance-96-2-84
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-96-2-846bedd78
bfcl-live-irrelevance-97-2-85
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-97-2-856bedd78
bfcl-live-irrelevance-98-2-86
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-98-2-866bedd78
bfcl-live-irrelevance-99-2-87
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-99-2-876bedd78
bfcl-live-multiple-0-0-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-0-0-06bedd78
bfcl-live-multiple-1-0-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1-0-16bedd78
bfcl-live-multiple-10-4-2
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-10-4-26bedd78
bfcl-live-multiple-100-42-4
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-100-42-46bedd78
bfcl-live-multiple-1000-231-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1000-231-06bedd78
bfcl-live-multiple-1001-232-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1001-232-06bedd78
bfcl-live-multiple-1002-232-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1002-232-16bedd78
bfcl-live-multiple-1003-232-2
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1003-232-26bedd78
bfcl-live-multiple-1004-233-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1004-233-06bedd78
bfcl-live-multiple-1005-234-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1005-234-06bedd78
bfcl-live-multiple-1006-235-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1006-235-06bedd78
bfcl-live-multiple-1007-236-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1007-236-06bedd78
bfcl-live-multiple-1008-237-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1008-237-06bedd78
bfcl-live-multiple-1009-238-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1009-238-06bedd78
bfcl-live-multiple-101-42-5
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-101-42-56bedd78
bfcl-live-multiple-1010-239-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1010-239-06bedd78
bfcl-live-multiple-1011-240-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1011-240-06bedd78
bfcl-live-multiple-1012-241-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1012-241-06bedd78
bfcl-live-multiple-1013-242-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1013-242-06bedd78
bfcl-live-multiple-1014-243-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1014-243-06bedd78
bfcl-live-multiple-1015-244-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1015-244-06bedd78
bfcl-live-multiple-1016-245-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1016-245-06bedd78
bfcl-live-multiple-1017-246-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1017-246-06bedd78
bfcl-live-multiple-1018-247-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1018-247-06bedd78
bfcl-live-multiple-1019-248-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1019-248-06bedd78
bfcl-live-multiple-102-43-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-102-43-06bedd78
bfcl-live-multiple-1020-249-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1020-249-06bedd78
bfcl-live-multiple-1021-250-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1021-250-06bedd78
bfcl-live-multiple-1022-251-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1022-251-06bedd78
bfcl-live-multiple-1023-252-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1023-252-06bedd78
bfcl-live-multiple-1024-253-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1024-253-06bedd78
bfcl-live-multiple-1025-254-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1025-254-06bedd78
bfcl-live-multiple-1026-255-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1026-255-06bedd78
bfcl-live-multiple-1027-255-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1027-255-16bedd78
bfcl-live-multiple-1028-256-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1028-256-06bedd78
bfcl-live-multiple-1029-257-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1029-257-06bedd78
bfcl-live-multiple-103-43-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-103-43-16bedd78
bfcl-live-multiple-1030-258-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1030-258-06bedd78
bfcl-live-multiple-1031-259-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1031-259-06bedd78
bfcl-live-multiple-1032-260-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1032-260-06bedd78
bfcl-live-multiple-1033-261-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1033-261-06bedd78
bfcl-live-multiple-1034-262-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1034-262-06bedd78
bfcl-live-multiple-1035-263-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1035-263-06bedd78
bfcl-live-multiple-1036-263-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1036-263-16bedd78
bfcl-live-multiple-1037-264-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1037-264-06bedd78
bfcl-live-multiple-1038-265-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1038-265-06bedd78
bfcl-live-multiple-1039-266-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1039-266-06bedd78
bfcl-live-multiple-104-43-2
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-104-43-26bedd78
bfcl-live-multiple-1040-267-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1040-267-06bedd78
bfcl-live-multiple-1041-268-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1041-268-06bedd78
bfcl-live-multiple-1042-269-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1042-269-06bedd78
bfcl-live-multiple-1043-270-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1043-270-06bedd78
bfcl-live-multiple-1044-271-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1044-271-06bedd78
bfcl-live-multiple-1045-272-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1045-272-06bedd78
bfcl-live-multiple-1046-273-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1046-273-06bedd78
bfcl-live-multiple-1047-274-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1047-274-06bedd78
bfcl-live-multiple-1048-275-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1048-275-06bedd78
bfcl-live-multiple-1049-276-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1049-276-06bedd78
bfcl-live-multiple-105-43-3
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-105-43-36bedd78
bfcl-live-multiple-1050-277-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1050-277-06bedd78
bfcl-live-multiple-1051-278-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1051-278-06bedd78
bfcl-live-multiple-1052-279-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-1052-279-06bedd78
bfcl-live-multiple-106-43-4
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-106-43-46bedd78
bfcl-live-multiple-107-43-5
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-107-43-56bedd78
bfcl-live-multiple-108-43-6
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-108-43-66bedd78
bfcl-live-multiple-109-43-7
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-109-43-76bedd78
bfcl-live-multiple-11-4-3
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-11-4-36bedd78
bfcl-live-multiple-110-43-8
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-110-43-86bedd78
bfcl-live-multiple-111-43-9
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-111-43-96bedd78
bfcl-live-multiple-112-43-10
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-112-43-106bedd78
bfcl-live-multiple-113-44-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-113-44-06bedd78
bfcl-live-multiple-114-44-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-114-44-16bedd78
bfcl-live-multiple-115-45-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-115-45-06bedd78
bfcl-live-multiple-116-45-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-116-45-16bedd78
bfcl-live-multiple-117-45-2
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-117-45-26bedd78
bfcl-live-multiple-118-45-3
uvx harbor run -d bfcl@1.0 -t bfcl-live-multiple-118-45-36bedd78