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-602-193-4
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-602-193-4
6bedd78
bfcl-live-irrelevance-603-193-5
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-603-193-5
6bedd78
bfcl-live-irrelevance-604-193-6
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-604-193-6
6bedd78
bfcl-live-irrelevance-605-193-7
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-605-193-7
6bedd78
bfcl-live-irrelevance-606-193-8
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-606-193-8
6bedd78
bfcl-live-irrelevance-607-194-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-607-194-0
6bedd78
bfcl-live-irrelevance-608-194-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-608-194-1
6bedd78
bfcl-live-irrelevance-609-194-2
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-609-194-2
6bedd78
bfcl-live-irrelevance-61-2-49
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-61-2-49
6bedd78
bfcl-live-irrelevance-610-194-3
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-610-194-3
6bedd78
bfcl-live-irrelevance-611-194-4
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-611-194-4
6bedd78
bfcl-live-irrelevance-612-195-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-612-195-0
6bedd78
bfcl-live-irrelevance-613-195-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-613-195-1
6bedd78
bfcl-live-irrelevance-614-195-2
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-614-195-2
6bedd78
bfcl-live-irrelevance-615-195-3
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-615-195-3
6bedd78
bfcl-live-irrelevance-616-195-4
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-616-195-4
6bedd78
bfcl-live-irrelevance-617-195-5
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-617-195-5
6bedd78
bfcl-live-irrelevance-618-195-6
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-618-195-6
6bedd78
bfcl-live-irrelevance-619-196-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-619-196-0
6bedd78
bfcl-live-irrelevance-62-2-50
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-62-2-50
6bedd78
bfcl-live-irrelevance-620-196-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-620-196-1
6bedd78
bfcl-live-irrelevance-621-196-2
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-621-196-2
6bedd78
bfcl-live-irrelevance-622-196-3
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-622-196-3
6bedd78
bfcl-live-irrelevance-623-196-4
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-623-196-4
6bedd78
bfcl-live-irrelevance-624-197-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-624-197-0
6bedd78
bfcl-live-irrelevance-625-197-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-625-197-1
6bedd78
bfcl-live-irrelevance-626-198-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-626-198-0
6bedd78
bfcl-live-irrelevance-627-198-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-627-198-1
6bedd78
bfcl-live-irrelevance-628-199-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-628-199-0
6bedd78
bfcl-live-irrelevance-629-199-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-629-199-1
6bedd78
bfcl-live-irrelevance-63-2-51
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-63-2-51
6bedd78
bfcl-live-irrelevance-630-199-2
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-630-199-2
6bedd78
bfcl-live-irrelevance-631-200-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-631-200-0
6bedd78
bfcl-live-irrelevance-632-201-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-632-201-0
6bedd78
bfcl-live-irrelevance-633-201-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-633-201-1
6bedd78
bfcl-live-irrelevance-634-201-2
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-634-201-2
6bedd78
bfcl-live-irrelevance-635-201-3
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-635-201-3
6bedd78
bfcl-live-irrelevance-636-202-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-636-202-0
6bedd78
bfcl-live-irrelevance-637-202-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-637-202-1
6bedd78
bfcl-live-irrelevance-638-202-2
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-638-202-2
6bedd78
bfcl-live-irrelevance-639-202-3
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-639-202-3
6bedd78
bfcl-live-irrelevance-64-2-52
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-64-2-52
6bedd78
bfcl-live-irrelevance-640-203-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-640-203-0
6bedd78
bfcl-live-irrelevance-641-203-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-641-203-1
6bedd78
bfcl-live-irrelevance-642-203-2
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-642-203-2
6bedd78
bfcl-live-irrelevance-643-203-3
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-643-203-3
6bedd78
bfcl-live-irrelevance-644-204-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-644-204-0
6bedd78
bfcl-live-irrelevance-645-204-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-645-204-1
6bedd78
bfcl-live-irrelevance-646-205-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-646-205-0
6bedd78
bfcl-live-irrelevance-647-205-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-647-205-1
6bedd78
bfcl-live-irrelevance-648-205-2
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-648-205-2
6bedd78
bfcl-live-irrelevance-649-205-3
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-649-205-3
6bedd78
bfcl-live-irrelevance-65-2-53
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-65-2-53
6bedd78
bfcl-live-irrelevance-650-205-4
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-650-205-4
6bedd78
bfcl-live-irrelevance-651-206-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-651-206-0
6bedd78
bfcl-live-irrelevance-652-206-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-652-206-1
6bedd78
bfcl-live-irrelevance-653-206-2
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-653-206-2
6bedd78
bfcl-live-irrelevance-654-206-3
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-654-206-3
6bedd78
bfcl-live-irrelevance-655-207-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-655-207-0
6bedd78
bfcl-live-irrelevance-656-208-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-656-208-0
6bedd78
bfcl-live-irrelevance-657-209-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-657-209-0
6bedd78
bfcl-live-irrelevance-658-209-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-658-209-1
6bedd78
bfcl-live-irrelevance-659-210-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-659-210-0
6bedd78
bfcl-live-irrelevance-66-2-54
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-66-2-54
6bedd78
bfcl-live-irrelevance-660-211-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-660-211-0
6bedd78
bfcl-live-irrelevance-661-211-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-661-211-1
6bedd78
bfcl-live-irrelevance-662-211-2
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-662-211-2
6bedd78
bfcl-live-irrelevance-663-211-3
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-663-211-3
6bedd78
bfcl-live-irrelevance-664-211-4
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-664-211-4
6bedd78
bfcl-live-irrelevance-665-211-5
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-665-211-5
6bedd78
bfcl-live-irrelevance-666-212-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-666-212-0
6bedd78
bfcl-live-irrelevance-667-212-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-667-212-1
6bedd78
bfcl-live-irrelevance-668-213-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-668-213-0
6bedd78
bfcl-live-irrelevance-669-213-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-669-213-1
6bedd78
bfcl-live-irrelevance-67-2-55
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-67-2-55
6bedd78
bfcl-live-irrelevance-670-213-2
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-670-213-2
6bedd78
bfcl-live-irrelevance-671-214-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-671-214-0
6bedd78
bfcl-live-irrelevance-672-215-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-672-215-0
6bedd78
bfcl-live-irrelevance-673-215-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-673-215-1
6bedd78
bfcl-live-irrelevance-674-215-2
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-674-215-2
6bedd78
bfcl-live-irrelevance-675-216-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-675-216-0
6bedd78
bfcl-live-irrelevance-676-217-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-676-217-0
6bedd78
bfcl-live-irrelevance-677-218-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-677-218-0
6bedd78
bfcl-live-irrelevance-678-219-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-678-219-0
6bedd78
bfcl-live-irrelevance-679-219-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-679-219-1
6bedd78
bfcl-live-irrelevance-68-2-56
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-68-2-56
6bedd78
bfcl-live-irrelevance-680-220-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-680-220-0
6bedd78
bfcl-live-irrelevance-681-220-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-681-220-1
6bedd78
bfcl-live-irrelevance-682-221-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-682-221-0
6bedd78
bfcl-live-irrelevance-683-221-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-683-221-1
6bedd78
bfcl-live-irrelevance-684-222-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-684-222-0
6bedd78
bfcl-live-irrelevance-685-223-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-685-223-0
6bedd78
bfcl-live-irrelevance-686-223-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-686-223-1
6bedd78
bfcl-live-irrelevance-687-223-2
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-687-223-2
6bedd78
bfcl-live-irrelevance-688-223-3
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-688-223-3
6bedd78
bfcl-live-irrelevance-689-224-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-689-224-0
6bedd78
bfcl-live-irrelevance-69-2-57
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-69-2-57
6bedd78
bfcl-live-irrelevance-690-225-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-690-225-0
6bedd78
bfcl-live-irrelevance-691-225-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-691-225-1
6bedd78
bfcl-live-irrelevance-692-225-2
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-692-225-2
6bedd78