{"adoption": {"forks": 276, "observed_at": "2026-08-28T04:08:14.871611+00:00", "stars": 3695}, "canonical_url": "https://ross.abutalabs.com/products/agentbench", "card": {"archived": false, "artifact_type": "dataset", "description": "A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)", "domain": ["large-language-models", "machine-learning", "developer-tools"], "enriched": true, "function": ["benchmarking", "agent-framework", "llm-inference", "testing"], "health_score": 60, "homepage": null, "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["THUDM/AgentBench"], "name": "THUDM/AgentBench", "platform": ["python", "cross-platform"], "pushed_at": "2026-02-08T17:01:05+00:00", "repo": "THUDM/AgentBench", "stars": 3695, "tags": ["llm-agents", "evaluation", "function-calling", "reinforcement-learning", "leaderboard", "iclr", "ai-agents", "docker", "linux"], "topics": ["chatgpt", "gpt-4", "llm", "llm-agent"], "urls": [], "use_cases": ["benchmark how well LLMs perform as agents on multi-turn tasks", "compare function-calling abilities of different LLMs", "evaluate agents on OS interaction and database tasks", "run containerized agent evaluation environments", "train agents with RL using AgentRL integration"], "what_it_is": "AgentBench is a comprehensive benchmark for evaluating large language models as agents across multi-turn interactive tasks like database querying, OS interaction, web shopping, and knowledge graph reasoning. The current version integrates with AgentRL and uses function-calling style prompts with fully containerized Docker Compose deployment.", "when_to_avoid": ["you need a simple single-task eval harness", "you cannot run Docker or provide large Freebase data", "you only want static dataset benchmarks without interactive environments"], "when_to_choose": ["you need standardized multi-environment evaluation of LLM agents", "you want reproducible, containerized agent benchmarks", "you are comparing function-calling performance across models"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/agentbench", "repo": "THUDM/AgentBench", "role": "main", "score": 58}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:08:14.871611+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T18:31:05.159501+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ce80fc649420bf9d933261aa2625d3a75571ed93adf91c3458e71a30f1f09b34", "fetched_at": "2026-08-28T04:08:14.871611+00:00", "kind": "readme", "missing": false, "url": "https://github.com/THUDM/AgentBench"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:08:14.871611+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T18:31:05.159501+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ce80fc649420bf9d933261aa2625d3a75571ed93adf91c3458e71a30f1f09b34", "fetched_at": "2026-08-28T04:08:14.871611+00:00", "kind": "readme", "missing": false, "url": "https://github.com/THUDM/AgentBench"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T18:31:05.159501+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ce80fc649420bf9d933261aa2625d3a75571ed93adf91c3458e71a30f1f09b34", "fetched_at": "2026-08-28T04:08:14.871611+00:00", "kind": "readme", "missing": false, "url": "https://github.com/THUDM/AgentBench"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:08:14.871611+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:08:14.871611+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:08:14.871611+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T18:31:05.159501+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ce80fc649420bf9d933261aa2625d3a75571ed93adf91c3458e71a30f1f09b34", "fetched_at": "2026-08-28T04:08:14.871611+00:00", "kind": "readme", "missing": false, "url": "https://github.com/THUDM/AgentBench"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:08:14.871611+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:08:14.871611+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T18:31:05.159501+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ce80fc649420bf9d933261aa2625d3a75571ed93adf91c3458e71a30f1f09b34", "fetched_at": "2026-08-28T04:08:14.871611+00:00", "kind": "readme", "missing": false, "url": "https://github.com/THUDM/AgentBench"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:08:14.871611+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:08:14.871611+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:08:14.871611+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T18:31:05.159501+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ce80fc649420bf9d933261aa2625d3a75571ed93adf91c3458e71a30f1f09b34", "fetched_at": "2026-08-28T04:08:14.871611+00:00", "kind": "readme", "missing": false, "url": "https://github.com/THUDM/AgentBench"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:08:14.871611+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:08:14.871611+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T18:31:05.159501+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ce80fc649420bf9d933261aa2625d3a75571ed93adf91c3458e71a30f1f09b34", "fetched_at": "2026-08-28T04:08:14.871611+00:00", "kind": "readme", "missing": false, "url": "https://github.com/THUDM/AgentBench"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T18:31:05.159501+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ce80fc649420bf9d933261aa2625d3a75571ed93adf91c3458e71a30f1f09b34", "fetched_at": "2026-08-28T04:08:14.871611+00:00", "kind": "readme", "missing": false, "url": "https://github.com/THUDM/AgentBench"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T18:31:05.159501+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ce80fc649420bf9d933261aa2625d3a75571ed93adf91c3458e71a30f1f09b34", "fetched_at": "2026-08-28T04:08:14.871611+00:00", "kind": "readme", "missing": false, "url": "https://github.com/THUDM/AgentBench"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T18:31:05.159501+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ce80fc649420bf9d933261aa2625d3a75571ed93adf91c3458e71a30f1f09b34", "fetched_at": "2026-08-28T04:08:14.871611+00:00", "kind": "readme", "missing": false, "url": "https://github.com/THUDM/AgentBench"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 66, "longevity": 80, "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": 1132, "days_push": 206, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 58, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}