{"record": {"aliases": [], "artifacts": [{"id": "gh:crispyberry/openbenchmark", "kind": "repo", "url": "https://github.com/crispyberry/OpenBenchmark"}, {"kind": "website", "url": "https://pi.dev"}], "categories": ["Agents", "General AI", "Language & Knowledge"], "description": {"en": "Evaluates AI agents and models on user-defined tasks generated from imported agent trajectories, scoring correctness, cost, and speed."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://github.com/crispyberry/OpenBenchmark", "source": "claire_radar", "source_url": "https://github.com/crispyberry/OpenBenchmark", "title": "OpenBenchmark"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:github:crispyberry/openbenchmark", "modality": null, "name": "OpenBenchmark", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "Medium", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-candidate", "display_eligible": "false", "origin_record_id": "bm_openbenchmark_199b1148", "origin_source": "github", "recognition_confidence": "0.4", "record_sha256": "f51a638b7ecd9389276944ab70a875cf390f64c51c4ee1c4a1742da9d0a95597", "relation": "unclear", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-08-25T17:43:56.718736Z", "source_url": "https://github.com/crispyberry/OpenBenchmark"}, "publisher": null, "released": "2026-08-20", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:github:crispyberry/openbenchmark", "source_url": "https://github.com/crispyberry/OpenBenchmark"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-github-crispyberry-openbenchmark", "source": "claire_radar", "source_benchmark_id": "github:crispyberry/openbenchmark", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/crispyberry/OpenBenchmark", "githubScope": "benchmark_repo", "githubStars": 1, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": null, "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"state": "not_applicable"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "A niche developer tool with moderate discovery potential from GitHub search and the multilingual README, but no academic paper or community evidence is provided to drive initial attention.", "score": 30}, "capabilities": [], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-25T17:43:56.718736Z", "inputHash": "9021bec27711d896be6d7d85022ab763e4836dbca4de291a4ec7ee56e125a0cc", "model": "deepseek-v4-pro"}, "curation": {"decisionReason": "The repository provides extensive documentation and code, but no independent paper, OpenReview entry, or official benchmark site is supplied; only a GitHub README is available, so the formal release status is unclear.", "model": "deepseek-v4-pro", "reviewedAt": "2026-08-25T17:43:56.718736Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-candidate", "demo": false, "description": "Evaluates AI agents and models on user-defined tasks generated from imported agent trajectories, scoring correctness, cost, and speed.", "discoverySources": [{"id": "github:crispyberry/openbenchmark", "type": "github", "url": "https://github.com/crispyberry/OpenBenchmark"}], "displayEligible": false, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "score_submission", "evidence": {"reasonCodes": ["discovered via github", "benchmark term in abstract", "evaluation protocol evidence", "public artifact URL", "no explicit benchmark release evidence"], "snippet": "ai-agents benchmark evaluation llm llm-evaluation nextjs observability openrouter postgres typescript # OpenBenchmark **English** · [简体中文](README.zh-CN.md) · [日本語](README.ja.md) · [Français](README.fr.md) · [Español](README.es.md) **Turn real agent trajectories into runnable benchmarks, then rank models, harnesses, and your own agents on score, cost, and speed.** Standard benchmarks tell you which model is good at someone else's problem."}, "familyId": "bmf_9da9d25e3255", "firstSeenAt": "2026-08-23", "heat": null, "id": "bm_openbenchmark_199b1148", "indexedAt": "2026-08-23T06:55:51.988821Z", "industrySectors": [], "links": {"code": "https://github.com/crispyberry/OpenBenchmark", "project": "https://pi.dev"}, "metrics": [], "motivation": "OpenBenchmark Turn real agent trajectories into runnable benchmarks, then rank models, harnesses, and your own agents on score, cost, and speed.", "name": "OpenBenchmark", "oneLine": "Evaluates AI agents and models on user-defined tasks generated from imported agent trajectories, scoring correctness, cost, and speed.", "paperTitle": "OpenBenchmark", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://github.com/crispyberry/OpenBenchmark", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-23T06:55:51.988821Z"}, "publications": [], "ranking": {"90d": {"confidence": "Low", "coverage": 0.55, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 90}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": 0.09252268850709358, "value": 1}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 334, "score": 28}, "method": "attention-ranking-v13", "rank": 334, "score": 28}}, "readiness": "Runnable", "recognitionConfidence": 0.4, "relation": "unclear", "releasedAt": "2026-08-20", "source": {"authors": ["crispyberry"], "categories": [], "id": "github:crispyberry/openbenchmark", "title": "OpenBenchmark", "type": "github", "url": "https://github.com/crispyberry/OpenBenchmark"}, "sourceUpdatedAt": "2026-08-21T08:44:17Z", "topics": ["Agents"], "venueAttempts": [], "whyItMatters": "Enables organizations to build benchmarks from their own agent logs, producing rankings that reflect real operational workloads rather than generic tasks."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
