{"adoption": {"forks": 489, "observed_at": "2026-08-28T04:09:28.323624+00:00", "stars": 5732}, "canonical_url": "https://ross.abutalabs.com/products/toolbench", "card": {"archived": false, "artifact_type": "dataset", "description": "[ICLR'24 spotlight] An open platform for training, serving, and evaluating large language model for tool learning.", "domain": ["large-language-models", "machine-learning"], "enriched": true, "function": ["llm-training", "agent-framework", "benchmarking", "rag"], "health_score": 34, "homepage": "https://openbmb.github.io/ToolBench/", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["OpenBMB/ToolBench"], "name": "OpenBMB/ToolBench", "platform": ["python"], "pushed_at": "2025-05-21T15:46:59+00:00", "repo": "OpenBMB/ToolBench", "stars": 5732, "tags": ["tool-learning", "instruction-tuning", "function-calling", "api-use", "tooleval", "toolllama", "iclr-2024", "ai-agents", "natural-language-processing", "linux", "docker"], "topics": [], "urls": [], "use_cases": ["train an LLM to call real-world APIs", "evaluate tool-use capabilities of language models", "generate instruction tuning data for function calling", "benchmark my agent against ChatGPT on tool use", "fine-tune an open-source model for tool learning", "compare models on a tool-use leaderboard"], "what_it_is": "ToolBench is an open-source platform for training, serving, and evaluating large language models on tool use, built around a large-scale instruction-tuning dataset covering thousands of real-world APIs. It includes the ToolLLaMA fine-tuned model, data generation pipelines, and the ToolEval automatic evaluator with a leaderboard.", "when_to_avoid": ["you only need a production agent framework rather than training/evaluation research tooling", "you cannot access OpenAI APIs or the RapidAPI tool server", "you need a stable offline evaluation environment without setting up StableToolBench separately"], "when_to_choose": ["you need SFT data or a benchmark for LLM tool/API use", "you want to fine-tune or evaluate open models on function calling", "you need an automatic evaluator (pass rate / win rate) for tool-learning agents"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/toolbench", "repo": "OpenBMB/ToolBench", "role": "main", "score": 39}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:09:28.323624+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:53:23.346974+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "92cac552fef0026ae0954bbab01d10a43a47984ef409d8bc5200bf05b531c76e", "fetched_at": "2026-08-28T04:09:28.323624+00:00", "kind": "readme", "missing": false, "url": "https://github.com/OpenBMB/ToolBench"}, {"content_hash": "8f626240f45fec6d48efad00da135a887a859b654e311ee7edb67663a6b4f01b", "fetched_at": "2026-08-29T08:48:48.782318+00:00", "kind": "homepage", "missing": false, "url": "https://openbmb.github.io/ToolBench/"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:09:28.323624+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:53:23.346974+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "92cac552fef0026ae0954bbab01d10a43a47984ef409d8bc5200bf05b531c76e", "fetched_at": "2026-08-28T04:09:28.323624+00:00", "kind": "readme", "missing": false, "url": "https://github.com/OpenBMB/ToolBench"}, {"content_hash": "8f626240f45fec6d48efad00da135a887a859b654e311ee7edb67663a6b4f01b", "fetched_at": "2026-08-29T08:48:48.782318+00:00", "kind": "homepage", "missing": false, "url": "https://openbmb.github.io/ToolBench/"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:53:23.346974+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "92cac552fef0026ae0954bbab01d10a43a47984ef409d8bc5200bf05b531c76e", "fetched_at": "2026-08-28T04:09:28.323624+00:00", "kind": "readme", "missing": false, "url": "https://github.com/OpenBMB/ToolBench"}, {"content_hash": "8f626240f45fec6d48efad00da135a887a859b654e311ee7edb67663a6b4f01b", "fetched_at": "2026-08-29T08:48:48.782318+00:00", "kind": "homepage", "missing": false, "url": "https://openbmb.github.io/ToolBench/"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:09:28.323624+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:09:28.323624+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:09:28.323624+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:53:23.346974+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "92cac552fef0026ae0954bbab01d10a43a47984ef409d8bc5200bf05b531c76e", "fetched_at": "2026-08-28T04:09:28.323624+00:00", "kind": "readme", "missing": false, "url": "https://github.com/OpenBMB/ToolBench"}, {"content_hash": "8f626240f45fec6d48efad00da135a887a859b654e311ee7edb67663a6b4f01b", "fetched_at": "2026-08-29T08:48:48.782318+00:00", "kind": "homepage", "missing": false, "url": "https://openbmb.github.io/ToolBench/"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:09:28.323624+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:09:28.323624+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:53:23.346974+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "92cac552fef0026ae0954bbab01d10a43a47984ef409d8bc5200bf05b531c76e", "fetched_at": "2026-08-28T04:09:28.323624+00:00", "kind": "readme", "missing": false, "url": "https://github.com/OpenBMB/ToolBench"}, {"content_hash": "8f626240f45fec6d48efad00da135a887a859b654e311ee7edb67663a6b4f01b", "fetched_at": "2026-08-29T08:48:48.782318+00:00", "kind": "homepage", "missing": false, "url": "https://openbmb.github.io/ToolBench/"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:09:28.323624+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:09:28.323624+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:09:28.323624+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:53:23.346974+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "92cac552fef0026ae0954bbab01d10a43a47984ef409d8bc5200bf05b531c76e", "fetched_at": "2026-08-28T04:09:28.323624+00:00", "kind": "readme", "missing": false, "url": "https://github.com/OpenBMB/ToolBench"}, {"content_hash": "8f626240f45fec6d48efad00da135a887a859b654e311ee7edb67663a6b4f01b", "fetched_at": "2026-08-29T08:48:48.782318+00:00", "kind": "homepage", "missing": false, "url": "https://openbmb.github.io/ToolBench/"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:09:28.323624+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:09:28.323624+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:53:23.346974+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "92cac552fef0026ae0954bbab01d10a43a47984ef409d8bc5200bf05b531c76e", "fetched_at": "2026-08-28T04:09:28.323624+00:00", "kind": "readme", "missing": false, "url": "https://github.com/OpenBMB/ToolBench"}, {"content_hash": "8f626240f45fec6d48efad00da135a887a859b654e311ee7edb67663a6b4f01b", "fetched_at": "2026-08-29T08:48:48.782318+00:00", "kind": "homepage", "missing": false, "url": "https://openbmb.github.io/ToolBench/"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:53:23.346974+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "92cac552fef0026ae0954bbab01d10a43a47984ef409d8bc5200bf05b531c76e", "fetched_at": "2026-08-28T04:09:28.323624+00:00", "kind": "readme", "missing": false, "url": "https://github.com/OpenBMB/ToolBench"}, {"content_hash": "8f626240f45fec6d48efad00da135a887a859b654e311ee7edb67663a6b4f01b", "fetched_at": "2026-08-29T08:48:48.782318+00:00", "kind": "homepage", "missing": false, "url": "https://openbmb.github.io/ToolBench/"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:53:23.346974+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "92cac552fef0026ae0954bbab01d10a43a47984ef409d8bc5200bf05b531c76e", "fetched_at": "2026-08-28T04:09:28.323624+00:00", "kind": "readme", "missing": false, "url": "https://github.com/OpenBMB/ToolBench"}, {"content_hash": "8f626240f45fec6d48efad00da135a887a859b654e311ee7edb67663a6b4f01b", "fetched_at": "2026-08-29T08:48:48.782318+00:00", "kind": "homepage", "missing": false, "url": "https://openbmb.github.io/ToolBench/"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:53:23.346974+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "92cac552fef0026ae0954bbab01d10a43a47984ef409d8bc5200bf05b531c76e", "fetched_at": "2026-08-28T04:09:28.323624+00:00", "kind": "readme", "missing": false, "url": "https://github.com/OpenBMB/ToolBench"}, {"content_hash": "8f626240f45fec6d48efad00da135a887a859b654e311ee7edb67663a6b4f01b", "fetched_at": "2026-08-29T08:48:48.782318+00:00", "kind": "homepage", "missing": false, "url": "https://openbmb.github.io/ToolBench/"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 22, "longevity": 85, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1193, "days_push": 469, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 39, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}