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-422-100-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-422-100-0
6bedd78
bfcl-live-irrelevance-423-101-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-423-101-0
6bedd78
bfcl-live-irrelevance-424-101-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-424-101-1
6bedd78
bfcl-live-irrelevance-425-101-2
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-425-101-2
6bedd78
bfcl-live-irrelevance-426-102-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-426-102-0
6bedd78
bfcl-live-irrelevance-427-102-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-427-102-1
6bedd78
bfcl-live-irrelevance-428-103-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-428-103-0
6bedd78
bfcl-live-irrelevance-429-104-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-429-104-0
6bedd78
bfcl-live-irrelevance-43-2-31
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-43-2-31
6bedd78
bfcl-live-irrelevance-430-105-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-430-105-0
6bedd78
bfcl-live-irrelevance-431-106-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-431-106-0
6bedd78
bfcl-live-irrelevance-432-107-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-432-107-0
6bedd78
bfcl-live-irrelevance-433-107-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-433-107-1
6bedd78
bfcl-live-irrelevance-434-108-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-434-108-0
6bedd78
bfcl-live-irrelevance-435-108-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-435-108-1
6bedd78
bfcl-live-irrelevance-436-109-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-436-109-0
6bedd78
bfcl-live-irrelevance-437-109-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-437-109-1
6bedd78
bfcl-live-irrelevance-438-110-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-438-110-0
6bedd78
bfcl-live-irrelevance-439-110-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-439-110-1
6bedd78
bfcl-live-irrelevance-44-2-32
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-44-2-32
6bedd78
bfcl-live-irrelevance-440-111-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-440-111-0
6bedd78
bfcl-live-irrelevance-441-112-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-441-112-0
6bedd78
bfcl-live-irrelevance-442-113-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-442-113-0
6bedd78
bfcl-live-irrelevance-443-113-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-443-113-1
6bedd78
bfcl-live-irrelevance-444-114-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-444-114-0
6bedd78
bfcl-live-irrelevance-445-115-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-445-115-0
6bedd78
bfcl-live-irrelevance-446-116-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-446-116-0
6bedd78
bfcl-live-irrelevance-447-116-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-447-116-1
6bedd78
bfcl-live-irrelevance-448-117-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-448-117-0
6bedd78
bfcl-live-irrelevance-449-118-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-449-118-0
6bedd78
bfcl-live-irrelevance-45-2-33
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-45-2-33
6bedd78
bfcl-live-irrelevance-450-118-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-450-118-1
6bedd78
bfcl-live-irrelevance-451-119-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-451-119-0
6bedd78
bfcl-live-irrelevance-452-120-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-452-120-0
6bedd78
bfcl-live-irrelevance-453-121-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-453-121-0
6bedd78
bfcl-live-irrelevance-454-121-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-454-121-1
6bedd78
bfcl-live-irrelevance-455-122-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-455-122-0
6bedd78
bfcl-live-irrelevance-456-123-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-456-123-0
6bedd78
bfcl-live-irrelevance-457-124-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-457-124-0
6bedd78
bfcl-live-irrelevance-458-124-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-458-124-1
6bedd78
bfcl-live-irrelevance-459-125-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-459-125-0
6bedd78
bfcl-live-irrelevance-46-2-34
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-46-2-34
6bedd78
bfcl-live-irrelevance-460-125-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-460-125-1
6bedd78
bfcl-live-irrelevance-461-126-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-461-126-0
6bedd78
bfcl-live-irrelevance-462-127-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-462-127-0
6bedd78
bfcl-live-irrelevance-463-128-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-463-128-0
6bedd78
bfcl-live-irrelevance-464-128-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-464-128-1
6bedd78
bfcl-live-irrelevance-465-129-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-465-129-0
6bedd78
bfcl-live-irrelevance-466-129-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-466-129-1
6bedd78
bfcl-live-irrelevance-467-129-2
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-467-129-2
6bedd78
bfcl-live-irrelevance-468-130-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-468-130-0
6bedd78
bfcl-live-irrelevance-469-130-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-469-130-1
6bedd78
bfcl-live-irrelevance-47-2-35
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-47-2-35
6bedd78
bfcl-live-irrelevance-470-131-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-470-131-0
6bedd78
bfcl-live-irrelevance-471-131-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-471-131-1
6bedd78
bfcl-live-irrelevance-472-132-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-472-132-0
6bedd78
bfcl-live-irrelevance-473-132-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-473-132-1
6bedd78
bfcl-live-irrelevance-474-133-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-474-133-0
6bedd78
bfcl-live-irrelevance-475-133-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-475-133-1
6bedd78
bfcl-live-irrelevance-476-134-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-476-134-0
6bedd78
bfcl-live-irrelevance-477-134-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-477-134-1
6bedd78
bfcl-live-irrelevance-478-135-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-478-135-0
6bedd78
bfcl-live-irrelevance-479-135-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-479-135-1
6bedd78
bfcl-live-irrelevance-48-2-36
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-48-2-36
6bedd78
bfcl-live-irrelevance-480-136-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-480-136-0
6bedd78
bfcl-live-irrelevance-481-136-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-481-136-1
6bedd78
bfcl-live-irrelevance-482-137-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-482-137-0
6bedd78
bfcl-live-irrelevance-483-138-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-483-138-0
6bedd78
bfcl-live-irrelevance-484-138-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-484-138-1
6bedd78
bfcl-live-irrelevance-485-139-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-485-139-0
6bedd78
bfcl-live-irrelevance-486-140-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-486-140-0
6bedd78
bfcl-live-irrelevance-487-141-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-487-141-0
6bedd78
bfcl-live-irrelevance-488-141-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-488-141-1
6bedd78
bfcl-live-irrelevance-489-142-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-489-142-0
6bedd78
bfcl-live-irrelevance-49-2-37
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-49-2-37
6bedd78
bfcl-live-irrelevance-490-142-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-490-142-1
6bedd78
bfcl-live-irrelevance-491-142-2
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-491-142-2
6bedd78
bfcl-live-irrelevance-492-142-3
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-492-142-3
6bedd78
bfcl-live-irrelevance-493-142-4
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-493-142-4
6bedd78
bfcl-live-irrelevance-494-142-5
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-494-142-5
6bedd78
bfcl-live-irrelevance-495-142-6
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-495-142-6
6bedd78
bfcl-live-irrelevance-496-142-7
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-496-142-7
6bedd78
bfcl-live-irrelevance-497-143-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-497-143-0
6bedd78
bfcl-live-irrelevance-498-144-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-498-144-0
6bedd78
bfcl-live-irrelevance-499-145-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-499-145-0
6bedd78
bfcl-live-irrelevance-5-0-5
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-5-0-5
6bedd78
bfcl-live-irrelevance-50-2-38
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-50-2-38
6bedd78
bfcl-live-irrelevance-500-146-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-500-146-0
6bedd78
bfcl-live-irrelevance-501-146-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-501-146-1
6bedd78
bfcl-live-irrelevance-502-147-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-502-147-0
6bedd78
bfcl-live-irrelevance-503-148-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-503-148-0
6bedd78
bfcl-live-irrelevance-504-148-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-504-148-1
6bedd78
bfcl-live-irrelevance-505-148-2
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-505-148-2
6bedd78
bfcl-live-irrelevance-506-148-3
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-506-148-3
6bedd78
bfcl-live-irrelevance-507-149-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-507-149-0
6bedd78
bfcl-live-irrelevance-508-149-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-508-149-1
6bedd78
bfcl-live-irrelevance-509-150-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-509-150-0
6bedd78
bfcl-live-irrelevance-51-2-39
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-51-2-39
6bedd78
bfcl-live-irrelevance-510-150-1
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-510-150-1
6bedd78
bfcl-live-irrelevance-511-151-0
uvx harbor run -d bfcl@1.0 -t bfcl-live-irrelevance-511-151-0
6bedd78