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-332-77-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-332-77-06bedd78
bfcl-live-irrelevance-333-78-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-333-78-06bedd78
bfcl-live-irrelevance-334-78-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-334-78-16bedd78
bfcl-live-irrelevance-335-79-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-335-79-06bedd78
bfcl-live-irrelevance-336-79-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-336-79-16bedd78
bfcl-live-irrelevance-337-80-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-337-80-06bedd78
bfcl-live-irrelevance-338-80-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-338-80-16bedd78
bfcl-live-irrelevance-339-81-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-339-81-06bedd78
bfcl-live-irrelevance-34-2-22
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-34-2-226bedd78
bfcl-live-irrelevance-340-81-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-340-81-16bedd78
bfcl-live-irrelevance-341-81-2
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-341-81-26bedd78
bfcl-live-irrelevance-342-81-3
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-342-81-36bedd78
bfcl-live-irrelevance-343-81-4
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-343-81-46bedd78
bfcl-live-irrelevance-344-81-5
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-344-81-56bedd78
bfcl-live-irrelevance-345-81-6
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-345-81-66bedd78
bfcl-live-irrelevance-346-81-7
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-346-81-76bedd78
bfcl-live-irrelevance-347-81-8
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-347-81-86bedd78
bfcl-live-irrelevance-348-81-9
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-348-81-96bedd78
bfcl-live-irrelevance-349-81-10
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-349-81-106bedd78
bfcl-live-irrelevance-35-2-23
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-35-2-236bedd78
bfcl-live-irrelevance-350-81-11
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-350-81-116bedd78
bfcl-live-irrelevance-351-81-12
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-351-81-126bedd78
bfcl-live-irrelevance-352-81-13
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-352-81-136bedd78
bfcl-live-irrelevance-353-81-14
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-353-81-146bedd78
bfcl-live-irrelevance-354-81-15
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-354-81-156bedd78
bfcl-live-irrelevance-355-81-16
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-355-81-166bedd78
bfcl-live-irrelevance-356-81-17
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-356-81-176bedd78
bfcl-live-irrelevance-357-81-18
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-357-81-186bedd78
bfcl-live-irrelevance-358-81-19
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-358-81-196bedd78
bfcl-live-irrelevance-359-81-20
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-359-81-206bedd78
bfcl-live-irrelevance-36-2-24
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-36-2-246bedd78
bfcl-live-irrelevance-360-81-21
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-360-81-216bedd78
bfcl-live-irrelevance-361-81-22
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-361-81-226bedd78
bfcl-live-irrelevance-362-81-23
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-362-81-236bedd78
bfcl-live-irrelevance-363-81-24
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-363-81-246bedd78
bfcl-live-irrelevance-364-81-25
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-364-81-256bedd78
bfcl-live-irrelevance-365-81-26
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-365-81-266bedd78
bfcl-live-irrelevance-366-81-27
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-366-81-276bedd78
bfcl-live-irrelevance-367-81-28
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-367-81-286bedd78
bfcl-live-irrelevance-368-81-29
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-368-81-296bedd78
bfcl-live-irrelevance-369-81-30
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-369-81-306bedd78
bfcl-live-irrelevance-37-2-25
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-37-2-256bedd78
bfcl-live-irrelevance-370-81-31
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-370-81-316bedd78
bfcl-live-irrelevance-371-81-32
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-371-81-326bedd78
bfcl-live-irrelevance-372-81-33
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-372-81-336bedd78
bfcl-live-irrelevance-373-81-34
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-373-81-346bedd78
bfcl-live-irrelevance-374-81-35
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-374-81-356bedd78
bfcl-live-irrelevance-375-81-36
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-375-81-366bedd78
bfcl-live-irrelevance-376-81-37
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-376-81-376bedd78
bfcl-live-irrelevance-377-81-38
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-377-81-386bedd78
bfcl-live-irrelevance-378-81-39
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-378-81-396bedd78
bfcl-live-irrelevance-379-81-40
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-379-81-406bedd78
bfcl-live-irrelevance-38-2-26
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-38-2-266bedd78
bfcl-live-irrelevance-380-81-41
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-380-81-416bedd78
bfcl-live-irrelevance-381-81-42
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-381-81-426bedd78
bfcl-live-irrelevance-382-81-43
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-382-81-436bedd78
bfcl-live-irrelevance-383-81-44
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-383-81-446bedd78
bfcl-live-irrelevance-384-81-45
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-384-81-456bedd78
bfcl-live-irrelevance-385-81-46
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-385-81-466bedd78
bfcl-live-irrelevance-386-81-47
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-386-81-476bedd78
bfcl-live-irrelevance-387-81-48
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-387-81-486bedd78
bfcl-live-irrelevance-388-81-49
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-388-81-496bedd78
bfcl-live-irrelevance-389-81-50
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-389-81-506bedd78
bfcl-live-irrelevance-39-2-27
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-39-2-276bedd78
bfcl-live-irrelevance-390-81-51
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-390-81-516bedd78
bfcl-live-irrelevance-391-81-52
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-391-81-526bedd78
bfcl-live-irrelevance-392-81-53
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-392-81-536bedd78
bfcl-live-irrelevance-393-81-54
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-393-81-546bedd78
bfcl-live-irrelevance-394-81-55
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-394-81-556bedd78
bfcl-live-irrelevance-395-81-56
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-395-81-566bedd78
bfcl-live-irrelevance-396-81-57
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-396-81-576bedd78
bfcl-live-irrelevance-397-81-58
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-397-81-586bedd78
bfcl-live-irrelevance-398-81-59
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-398-81-596bedd78
bfcl-live-irrelevance-399-82-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-399-82-06bedd78
bfcl-live-irrelevance-4-0-4
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-4-0-46bedd78
bfcl-live-irrelevance-40-2-28
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-40-2-286bedd78
bfcl-live-irrelevance-400-83-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-400-83-06bedd78
bfcl-live-irrelevance-401-83-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-401-83-16bedd78
bfcl-live-irrelevance-402-84-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-402-84-06bedd78
bfcl-live-irrelevance-403-85-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-403-85-06bedd78
bfcl-live-irrelevance-404-86-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-404-86-06bedd78
bfcl-live-irrelevance-405-87-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-405-87-06bedd78
bfcl-live-irrelevance-406-88-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-406-88-06bedd78
bfcl-live-irrelevance-407-89-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-407-89-06bedd78
bfcl-live-irrelevance-408-90-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-408-90-06bedd78
bfcl-live-irrelevance-409-91-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-409-91-06bedd78
bfcl-live-irrelevance-41-2-29
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-41-2-296bedd78
bfcl-live-irrelevance-410-91-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-410-91-16bedd78
bfcl-live-irrelevance-411-92-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-411-92-06bedd78
bfcl-live-irrelevance-412-92-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-412-92-16bedd78
bfcl-live-irrelevance-413-93-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-413-93-06bedd78
bfcl-live-irrelevance-414-93-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-414-93-16bedd78
bfcl-live-irrelevance-415-94-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-415-94-06bedd78
bfcl-live-irrelevance-416-95-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-416-95-06bedd78
bfcl-live-irrelevance-417-96-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-417-96-06bedd78
bfcl-live-irrelevance-418-96-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-418-96-16bedd78
bfcl-live-irrelevance-419-97-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-419-97-06bedd78
bfcl-live-irrelevance-42-2-30
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-42-2-306bedd78
bfcl-live-irrelevance-420-98-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-420-98-06bedd78
bfcl-live-irrelevance-421-99-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-421-99-06bedd78