{"adoption": {"forks": 157, "observed_at": "2026-08-28T04:03:18.437814+00:00", "stars": 1033}, "canonical_url": "https://ross.abutalabs.com/products/harmbench", "card": {"archived": false, "artifact_type": "framework", "description": "HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal", "domain": ["artificial-intelligence", "large-language-models", "security", "machine-learning"], "enriched": true, "function": ["benchmarking", "testing", "llm-inference", "machine-learning"], "health_score": 20, "homepage": "https://harmbench.org", "language": "Jupyter Notebook", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["centerforaisafety/HarmBench"], "name": "centerforaisafety/HarmBench", "platform": ["python", "cli"], "pushed_at": "2024-08-16T04:37:37+00:00", "repo": "centerforaisafety/HarmBench", "stars": 1033, "tags": ["llm-safety", "red-teaming", "adversarial-attacks", "llm-evaluation", "jailbreaks", "ai-safety", "gpu"], "topics": [], "urls": [], "use_cases": ["benchmark LLM jailbreak attacks against multiple models", "evaluate how robust an LLM is to red teaming methods", "compare automated red teaming techniques on a standard test suite", "train LLMs to refuse harmful requests via adversarial training", "run safety evaluations before deploying an LLM"], "what_it_is": "HarmBench is a standardized, open-source evaluation framework for automated red teaming of large language models, comparing attack methods and defenses across many LLMs. It provides an evaluation pipeline, classifiers, precomputed test cases, and adversarial training code for improving LLM robustness.", "when_to_avoid": ["you need general-purpose ML benchmarking unrelated to LLM safety", "you want a lightweight safety filter for production rather than an evaluation harness", "your models are not LLMs"], "when_to_choose": ["you need a standardized benchmark for LLM attack/defense evaluation", "you want to compare many red teaming methods or target LLMs reproducibly", "you are researching LLM safety and adversarial robustness"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/harmbench", "repo": "centerforaisafety/HarmBench", "role": "main", "score": 26}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:18.437814+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T07:06:39.798996+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0995eb79bc8c53b78d8d16df37cad18cc31db337c76ea85825457c776970119f", "fetched_at": "2026-08-28T04:03:18.437814+00:00", "kind": "readme", "missing": false, "url": "https://github.com/centerforaisafety/HarmBench"}, {"content_hash": "a27fcb336529482399044b3b5040aeaaa825dd00413f6ab2734e47c14ebd551b", "fetched_at": "2026-08-29T13:06:37.835365+00:00", "kind": "homepage", "missing": false, "url": "https://harmbench.org"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:18.437814+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T07:06:39.798996+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0995eb79bc8c53b78d8d16df37cad18cc31db337c76ea85825457c776970119f", "fetched_at": "2026-08-28T04:03:18.437814+00:00", "kind": "readme", "missing": false, "url": "https://github.com/centerforaisafety/HarmBench"}, {"content_hash": "a27fcb336529482399044b3b5040aeaaa825dd00413f6ab2734e47c14ebd551b", "fetched_at": "2026-08-29T13:06:37.835365+00:00", "kind": "homepage", "missing": false, "url": "https://harmbench.org"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T07:06:39.798996+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0995eb79bc8c53b78d8d16df37cad18cc31db337c76ea85825457c776970119f", "fetched_at": "2026-08-28T04:03:18.437814+00:00", "kind": "readme", "missing": false, "url": "https://github.com/centerforaisafety/HarmBench"}, {"content_hash": "a27fcb336529482399044b3b5040aeaaa825dd00413f6ab2734e47c14ebd551b", "fetched_at": "2026-08-29T13:06:37.835365+00:00", "kind": "homepage", "missing": false, "url": "https://harmbench.org"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:18.437814+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:18.437814+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:18.437814+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T07:06:39.798996+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0995eb79bc8c53b78d8d16df37cad18cc31db337c76ea85825457c776970119f", "fetched_at": "2026-08-28T04:03:18.437814+00:00", "kind": "readme", "missing": false, "url": "https://github.com/centerforaisafety/HarmBench"}, {"content_hash": "a27fcb336529482399044b3b5040aeaaa825dd00413f6ab2734e47c14ebd551b", "fetched_at": "2026-08-29T13:06:37.835365+00:00", "kind": "homepage", "missing": false, "url": "https://harmbench.org"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:18.437814+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:18.437814+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T07:06:39.798996+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0995eb79bc8c53b78d8d16df37cad18cc31db337c76ea85825457c776970119f", "fetched_at": "2026-08-28T04:03:18.437814+00:00", "kind": "readme", "missing": false, "url": "https://github.com/centerforaisafety/HarmBench"}, {"content_hash": "a27fcb336529482399044b3b5040aeaaa825dd00413f6ab2734e47c14ebd551b", "fetched_at": "2026-08-29T13:06:37.835365+00:00", "kind": "homepage", "missing": false, "url": "https://harmbench.org"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:18.437814+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:18.437814+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:18.437814+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T07:06:39.798996+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0995eb79bc8c53b78d8d16df37cad18cc31db337c76ea85825457c776970119f", "fetched_at": "2026-08-28T04:03:18.437814+00:00", "kind": "readme", "missing": false, "url": "https://github.com/centerforaisafety/HarmBench"}, {"content_hash": "a27fcb336529482399044b3b5040aeaaa825dd00413f6ab2734e47c14ebd551b", "fetched_at": "2026-08-29T13:06:37.835365+00:00", "kind": "homepage", "missing": false, "url": "https://harmbench.org"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:18.437814+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:18.437814+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T07:06:39.798996+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0995eb79bc8c53b78d8d16df37cad18cc31db337c76ea85825457c776970119f", "fetched_at": "2026-08-28T04:03:18.437814+00:00", "kind": "readme", "missing": false, "url": "https://github.com/centerforaisafety/HarmBench"}, {"content_hash": "a27fcb336529482399044b3b5040aeaaa825dd00413f6ab2734e47c14ebd551b", "fetched_at": "2026-08-29T13:06:37.835365+00:00", "kind": "homepage", "missing": false, "url": "https://harmbench.org"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T07:06:39.798996+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0995eb79bc8c53b78d8d16df37cad18cc31db337c76ea85825457c776970119f", "fetched_at": "2026-08-28T04:03:18.437814+00:00", "kind": "readme", "missing": false, "url": "https://github.com/centerforaisafety/HarmBench"}, {"content_hash": "a27fcb336529482399044b3b5040aeaaa825dd00413f6ab2734e47c14ebd551b", "fetched_at": "2026-08-29T13:06:37.835365+00:00", "kind": "homepage", "missing": false, "url": "https://harmbench.org"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T07:06:39.798996+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0995eb79bc8c53b78d8d16df37cad18cc31db337c76ea85825457c776970119f", "fetched_at": "2026-08-28T04:03:18.437814+00:00", "kind": "readme", "missing": false, "url": "https://github.com/centerforaisafety/HarmBench"}, {"content_hash": "a27fcb336529482399044b3b5040aeaaa825dd00413f6ab2734e47c14ebd551b", "fetched_at": "2026-08-29T13:06:37.835365+00:00", "kind": "homepage", "missing": false, "url": "https://harmbench.org"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T07:06:39.798996+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0995eb79bc8c53b78d8d16df37cad18cc31db337c76ea85825457c776970119f", "fetched_at": "2026-08-28T04:03:18.437814+00:00", "kind": "readme", "missing": false, "url": "https://github.com/centerforaisafety/HarmBench"}, {"content_hash": "a27fcb336529482399044b3b5040aeaaa825dd00413f6ab2734e47c14ebd551b", "fetched_at": "2026-08-29T13:06:37.835365+00:00", "kind": "homepage", "missing": false, "url": "https://harmbench.org"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 67, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 943, "days_push": 747, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 26, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}