{"adoption": {"forks": 568, "observed_at": "2026-08-28T04:07:00.680973+00:00", "stars": 2554}, "canonical_url": "https://ross.abutalabs.com/products/terminal-bench-1", "card": {"archived": false, "artifact_type": "dataset", "description": "A benchmark for LLMs on complicated tasks in the terminal", "domain": ["large-language-models", "developer-tools"], "enriched": true, "function": ["benchmarking", "agent-framework", "testing", "cli"], "health_score": 75, "homepage": "https://www.tbench.ai", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["harbor-framework/terminal-bench-1"], "name": "harbor-framework/terminal-bench-1", "platform": ["python", "cli"], "pushed_at": "2026-07-11T05:19:08+00:00", "repo": "harbor-framework/terminal-bench-1", "stars": 2554, "tags": ["llm-benchmark", "terminal-agents", "evaluation-harness", "agent-evaluation", "sandbox", "ai-agents", "command-line", "docker", "linux", "macos"], "topics": [], "urls": [], "use_cases": ["benchmark llm agents on terminal tasks", "evaluate how well a model can use a shell autonomously", "compare coding agents on end-to-end system tasks", "run reproducible agent evaluations in a sandbox", "contribute new challenging tasks for agent testing"], "what_it_is": "Terminal-Bench is a benchmark and execution harness for evaluating LLM agents on complex, real-world tasks in a terminal sandbox. It combines a dataset of ~100+ terminal tasks with tooling that connects language models to the environment for reproducible evaluation.", "when_to_avoid": ["you need a general-purpose chat or reasoning benchmark rather than terminal tasks", "you want a lightweight unit-testing tool rather than an agent evaluation harness", "your agents operate in GUI or web environments rather than text terminals"], "when_to_choose": ["you need a standardized, reproducible benchmark for terminal-based agent capabilities", "you are building or stress-testing LLM agents that operate in a shell", "you want to compare models on real-world system-level tasks like compiling code or configuring servers"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/terminal-bench-1", "repo": "harbor-framework/terminal-bench-1", "role": "main", "score": 62}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:07:00.680973+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T02:23:44.562020+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c4bb406dbba0c10ed5ad2a4655f1f4c05f0b81dd9eabb3ca766fe0acdb9767c1", "fetched_at": "2026-08-28T04:07:00.680973+00:00", "kind": "readme", "missing": false, "url": "https://github.com/harbor-framework/terminal-bench-1"}, {"content_hash": "e42bdd88110e35d82d820a4205731cc120af51275a13ee1fe95514f055425fce", "fetched_at": "2026-08-29T10:06:22.893422+00:00", "kind": "homepage", "missing": false, "url": "https://www.tbench.ai"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:07:00.680973+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T02:23:44.562020+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c4bb406dbba0c10ed5ad2a4655f1f4c05f0b81dd9eabb3ca766fe0acdb9767c1", "fetched_at": "2026-08-28T04:07:00.680973+00:00", "kind": "readme", "missing": false, "url": "https://github.com/harbor-framework/terminal-bench-1"}, {"content_hash": "e42bdd88110e35d82d820a4205731cc120af51275a13ee1fe95514f055425fce", "fetched_at": "2026-08-29T10:06:22.893422+00:00", "kind": "homepage", "missing": false, "url": "https://www.tbench.ai"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T02:23:44.562020+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c4bb406dbba0c10ed5ad2a4655f1f4c05f0b81dd9eabb3ca766fe0acdb9767c1", "fetched_at": "2026-08-28T04:07:00.680973+00:00", "kind": "readme", "missing": false, "url": "https://github.com/harbor-framework/terminal-bench-1"}, {"content_hash": "e42bdd88110e35d82d820a4205731cc120af51275a13ee1fe95514f055425fce", "fetched_at": "2026-08-29T10:06:22.893422+00:00", "kind": "homepage", "missing": false, "url": "https://www.tbench.ai"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:07:00.680973+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:07:00.680973+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:07:00.680973+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T02:23:44.562020+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c4bb406dbba0c10ed5ad2a4655f1f4c05f0b81dd9eabb3ca766fe0acdb9767c1", "fetched_at": "2026-08-28T04:07:00.680973+00:00", "kind": "readme", "missing": false, "url": "https://github.com/harbor-framework/terminal-bench-1"}, {"content_hash": "e42bdd88110e35d82d820a4205731cc120af51275a13ee1fe95514f055425fce", "fetched_at": "2026-08-29T10:06:22.893422+00:00", "kind": "homepage", "missing": false, "url": "https://www.tbench.ai"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:07:00.680973+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:07:00.680973+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T02:23:44.562020+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c4bb406dbba0c10ed5ad2a4655f1f4c05f0b81dd9eabb3ca766fe0acdb9767c1", "fetched_at": "2026-08-28T04:07:00.680973+00:00", "kind": "readme", "missing": false, "url": "https://github.com/harbor-framework/terminal-bench-1"}, {"content_hash": "e42bdd88110e35d82d820a4205731cc120af51275a13ee1fe95514f055425fce", "fetched_at": "2026-08-29T10:06:22.893422+00:00", "kind": "homepage", "missing": false, "url": "https://www.tbench.ai"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:07:00.680973+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:07:00.680973+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:07:00.680973+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T02:23:44.562020+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c4bb406dbba0c10ed5ad2a4655f1f4c05f0b81dd9eabb3ca766fe0acdb9767c1", "fetched_at": "2026-08-28T04:07:00.680973+00:00", "kind": "readme", "missing": false, "url": "https://github.com/harbor-framework/terminal-bench-1"}, {"content_hash": "e42bdd88110e35d82d820a4205731cc120af51275a13ee1fe95514f055425fce", "fetched_at": "2026-08-29T10:06:22.893422+00:00", "kind": "homepage", "missing": false, "url": "https://www.tbench.ai"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:07:00.680973+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:07:00.680973+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T02:23:44.562020+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c4bb406dbba0c10ed5ad2a4655f1f4c05f0b81dd9eabb3ca766fe0acdb9767c1", "fetched_at": "2026-08-28T04:07:00.680973+00:00", "kind": "readme", "missing": false, "url": "https://github.com/harbor-framework/terminal-bench-1"}, {"content_hash": "e42bdd88110e35d82d820a4205731cc120af51275a13ee1fe95514f055425fce", "fetched_at": "2026-08-29T10:06:22.893422+00:00", "kind": "homepage", "missing": false, "url": "https://www.tbench.ai"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T02:23:44.562020+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c4bb406dbba0c10ed5ad2a4655f1f4c05f0b81dd9eabb3ca766fe0acdb9767c1", "fetched_at": "2026-08-28T04:07:00.680973+00:00", "kind": "readme", "missing": false, "url": "https://github.com/harbor-framework/terminal-bench-1"}, {"content_hash": "e42bdd88110e35d82d820a4205731cc120af51275a13ee1fe95514f055425fce", "fetched_at": "2026-08-29T10:06:22.893422+00:00", "kind": "homepage", "missing": false, "url": "https://www.tbench.ai"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T02:23:44.562020+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c4bb406dbba0c10ed5ad2a4655f1f4c05f0b81dd9eabb3ca766fe0acdb9767c1", "fetched_at": "2026-08-28T04:07:00.680973+00:00", "kind": "readme", "missing": false, "url": "https://github.com/harbor-framework/terminal-bench-1"}, {"content_hash": "e42bdd88110e35d82d820a4205731cc120af51275a13ee1fe95514f055425fce", "fetched_at": "2026-08-29T10:06:22.893422+00:00", "kind": "homepage", "missing": false, "url": "https://www.tbench.ai"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T02:23:44.562020+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c4bb406dbba0c10ed5ad2a4655f1f4c05f0b81dd9eabb3ca766fe0acdb9767c1", "fetched_at": "2026-08-28T04:07:00.680973+00:00", "kind": "readme", "missing": false, "url": "https://github.com/harbor-framework/terminal-bench-1"}, {"content_hash": "e42bdd88110e35d82d820a4205731cc120af51275a13ee1fe95514f055425fce", "fetched_at": "2026-08-29T10:06:22.893422+00:00", "kind": "homepage", "missing": false, "url": "https://www.tbench.ai"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 92, "longevity": 42, "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": 593, "days_push": 53, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 62, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}