Berkeley Function-Calling Leaderboard benchmark: evaluates LLM function-calling accuracy across single-turn (AST equality), multi-turn (executable runtime state comparison), and agentic (web search…
Free account. Installing gives you the manifest plus copy-paste snippets.
See reviewsImported from elizaOS/eliza (
packages/benchmarks/suites/bfcl/AGENTS.md). Install upstream withnpx skills add elizaOS/eliza --skill bfcl. Copyright stays with the author.
Berkeley Function-Calling Leaderboard benchmark: evaluates LLM function-calling accuracy across single-turn (AST equality), multi-turn (executable runtime state comparison), and agentic (web search, memory) categories.
Build, test, and setup: README.md.
Copy one of these into your project. Installing also returns the manifest and these snippets.
# after Install: the listing is in your workspace's routing pool - a plan picks it for its slot
curl -s -X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'Installed into a catalogue, chosen by a router
Photo: RDNE Stock project
An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.
{
"ocm": "1",
"id": "elizaos-eliza-bfcl",
"kind": "skill",
"name": "bfcl",
"description": "Berkeley Function-Calling Leaderboard benchmark: evaluates LLM function-calling accuracy across single-turn (AST equality), multi-turn (executable runtime state comparison), and agentic (web search, memory) categories.",
"publisher": "elizaOS",
"version": "1.0.0",
"capabilities": {
"domains": [
"coding"
],
"tags": [
"skill-md",
"github-agents"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Berkeley Function-Calling Leaderboard benchmark: evaluates LLM function-calling accuracy across single-turn (AST equality), multi-turn (executable runtime state comparison), and agentic (web search, memory) categories."
],
"primary": false,
"metadata": {
"source": {
"provider": "github-agents",
"repository": "https://github.com/elizaOS/eliza",
"path": "packages/benchmarks/suites/bfcl/AGENTS.md",
"ref": "07852e51fe8e1a2e0eae6e9e17f2bb925985910f",
"url": "https://github.com/elizaOS/eliza/blob/07852e51fe8e1a2e0eae6e9e17f2bb925985910f/packages/benchmarks/suites/bfcl/AGENTS.md",
"key": "elizaOS/eliza/packages/benchmarks/suites/bfcl/AGENTS.md"
}
},
"instructions": "# BFCL — Agent Guide\n\nBerkeley Function-Calling Leaderboard benchmark: evaluates LLM function-calling accuracy across single-turn (AST equality), multi-turn (executable runtime state comparison), and agentic (web search, memory) categories.\n\nBuild, test, and setup: [README.md](README.md).",
"cost": {
"context_tokens": 72
}
}Fetch it by URL: GET /api/v1/registry/elizaos-eliza-bfcl/manifest?version=1.0.0
Star ratings from people who tried it. One review per account; edit yours any time.
No reviews yet. Install it, try it, and be the first to rate it.