{"adoption": {"forks": 177, "observed_at": "2026-08-28T04:04:15.048672+00:00", "stars": 1287}, "canonical_url": "https://ross.abutalabs.com/products/frontier-evals", "card": {"archived": false, "artifact_type": "dataset", "description": "OpenAI Frontier Evals", "domain": ["artificial-intelligence", "large-language-models", "developer-tools", "security"], "enriched": true, "function": ["benchmarking", "testing"], "health_score": 67, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["openai/frontier-evals"], "name": "openai/frontier-evals", "platform": ["python", "cli"], "pushed_at": "2026-04-21T20:53:31+00:00", "repo": "openai/frontier-evals", "stars": 1287, "tags": ["llm-evals", "frontier-models", "paperbench", "swelancer", "evmbench", "model-capabilities", "ai-safety", "evaluation"], "topics": [], "urls": [], "use_cases": ["benchmark frontier LLM capabilities", "evaluate models on real freelance software engineering tasks", "test whether models can replicate state-of-the-art AI papers", "assess model performance on smart contract security tasks", "reproduce published OpenAI eval results", "compare model performance across capability benchmarks"], "what_it_is": "A collection of benchmark evaluations from OpenAI for measuring frontier LLM capabilities, including PaperBench (AI paper replication), SWE-Lancer (freelance software engineering tasks), and EVMbench (smart contract security). Each eval is an isolated Python project managed with uv.", "when_to_avoid": ["you need a general-purpose eval framework for building custom benchmarks", "you want lightweight model testing rather than heavyweight research-grade evals", "your use case is outside the included eval domains"], "when_to_choose": ["you need standardized benchmarks for evaluating frontier LLMs", "you want to reproduce results from OpenAI's published eval papers", "you're researching model capabilities in coding, research replication, or security"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/frontier-evals", "repo": "openai/frontier-evals", "role": "main", "score": 55}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:15.048672+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:56:06.336094+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5fce136159ab96a7a0e22bac8c9a56b9e6525d0e8013d93feb7f5e4daa0aa47d", "fetched_at": "2026-08-28T04:04:15.048672+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/frontier-evals"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:15.048672+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:56:06.336094+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5fce136159ab96a7a0e22bac8c9a56b9e6525d0e8013d93feb7f5e4daa0aa47d", "fetched_at": "2026-08-28T04:04:15.048672+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/frontier-evals"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:56:06.336094+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5fce136159ab96a7a0e22bac8c9a56b9e6525d0e8013d93feb7f5e4daa0aa47d", "fetched_at": "2026-08-28T04:04:15.048672+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/frontier-evals"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:15.048672+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:15.048672+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:15.048672+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:56:06.336094+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5fce136159ab96a7a0e22bac8c9a56b9e6525d0e8013d93feb7f5e4daa0aa47d", "fetched_at": "2026-08-28T04:04:15.048672+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/frontier-evals"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:15.048672+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:15.048672+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:56:06.336094+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5fce136159ab96a7a0e22bac8c9a56b9e6525d0e8013d93feb7f5e4daa0aa47d", "fetched_at": "2026-08-28T04:04:15.048672+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/frontier-evals"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:15.048672+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:15.048672+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:15.048672+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:56:06.336094+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5fce136159ab96a7a0e22bac8c9a56b9e6525d0e8013d93feb7f5e4daa0aa47d", "fetched_at": "2026-08-28T04:04:15.048672+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/frontier-evals"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:15.048672+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:15.048672+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:56:06.336094+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5fce136159ab96a7a0e22bac8c9a56b9e6525d0e8013d93feb7f5e4daa0aa47d", "fetched_at": "2026-08-28T04:04:15.048672+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/frontier-evals"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:56:06.336094+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5fce136159ab96a7a0e22bac8c9a56b9e6525d0e8013d93feb7f5e4daa0aa47d", "fetched_at": "2026-08-28T04:04:15.048672+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/frontier-evals"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:56:06.336094+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5fce136159ab96a7a0e22bac8c9a56b9e6525d0e8013d93feb7f5e4daa0aa47d", "fetched_at": "2026-08-28T04:04:15.048672+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/frontier-evals"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:56:06.336094+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5fce136159ab96a7a0e22bac8c9a56b9e6525d0e8013d93feb7f5e4daa0aa47d", "fetched_at": "2026-08-28T04:04:15.048672+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/frontier-evals"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 78, "longevity": 37, "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": 523, "days_push": 134, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 55, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}