{"record": {"aliases": ["llm-benchmark-panel"], "artifacts": [{"id": "gh:yunusbaysal/llm-benchmark-panel", "kind": "repo", "url": "https://github.com/yunusbaysal/llm-benchmark-panel"}], "categories": ["Finance", "Language & Knowledge", "cs.AI"], "description": {"en": "Multi-provider LLM benchmarking harness with task suites including reasoning, coding, and Turkish-language questions; scoring supports exact_match, keywords, regex, and optional llm_judge."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://github.com/yunusbaysal/llm-benchmark-panel", "source": "claire_radar", "source_url": "https://github.com/yunusbaysal/llm-benchmark-panel", "title": "LLM Benchmark Panel"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:github:yunusbaysal/llm-benchmark-panel", "modality": null, "name": "LLM Benchmark Panel", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"admission_policy_version": "2026-09-09.1", "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_llm-benchmark-panel_413dbe56", "origin_source": "github", "recognition_confidence": "0.4", "record_sha256": "ae3cf59d2b7cf1f07b6e7911be378d81de22bd0e8745a0c6d4f6849e7f3a8fe6", "relation": "unclear", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-09-10T06:21:31.238194Z", "source_url": "https://github.com/yunusbaysal/llm-benchmark-panel"}, "publisher": null, "released": "2026-09-08", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:github:yunusbaysal/llm-benchmark-panel", "source_url": "https://github.com/yunusbaysal/llm-benchmark-panel"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-github-yunusbaysal-llm-benchmark-panel", "source": "claire_radar", "source_benchmark_id": "github:yunusbaysal/llm-benchmark-panel", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": ["llm-benchmark-panel"], "annotation": "Mixed", "applicationDomains": ["Finance"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/yunusbaysal/llm-benchmark-panel", "githubScope": "benchmark_repo", "githubStars": 0, "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": "The project targets a broad LLM evaluation audience with task suites and dashboards, but artifacts are limited to a single repository with no paper or external publication to drive attention.", "score": 35}, "capabilities": [], "confidence": "Medium", "construction": "Aggregate Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-10T06:21:31.238194Z", "inputHash": "e9526949ed54c2be07ac1a1318da2032de9908472cc859f42d30021fcc9a73dd", "model": "deepseek-v4-pro"}, "curation": {"admissionPolicyVersion": "2026-09-09.1", "canonicalNameEvidence": "# LLM Benchmark Panel", "canonicalNameSource": "official_readme", "decisionReason": "The repository is a benchmarking harness with demo results, but it lacks a formally declared benchmark name, defined standard task suite, or external submission path; evidence of a stable scoring contract and public reuse is absent.", "evaluationEvidence": {"reuse": "A multi-provider LLM benchmarking harness: define task suites, run any mix of models against them, score responses (rule-based or LLM-as-judge), and get a static comparison dashboard — accuracy, latency, and cost, side by side.", "scoring": "score responses (rule-based or LLM-as-judge)", "task": "define task suites, run any mix of models against them"}, "model": "deepseek-v4-pro", "reviewedAt": "2026-09-10T06:21:31.238194Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-candidate", "demo": false, "description": "Multi-provider LLM benchmarking harness with task suites including reasoning, coding, and Turkish-language questions; scoring supports exact_match, keywords, regex, and optional llm_judge.", "discoverySources": [{"id": "github:yunusbaysal/llm-benchmark-panel", "type": "github", "url": "https://github.com/yunusbaysal/llm-benchmark-panel"}], "displayEligible": false, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["discovered via github", "benchmark term in abstract", "evaluation protocol evidence", "public artifact URL", "no explicit benchmark release evidence"], "snippet": "llm-benchmark-panel # LLM Benchmark Panel ![CI](https://github.com/yunusbaysal/llm-benchmark-panel/actions/workflows/ci.yml/badge.svg) ![Coverage](https://img.shields.io/badge/coverage-87%25-brightgreen) ![Python](https://img.shields.io/badge/python-3.10%20%7C%203.11%20%7C%203.12-blue) ![License](https://img.shields.io/badge/license-MIT-green) A multi-provider LLM benchmarking harness: define task suites, run any mix of models against them, score responses (rule-based or LLM-as-judge), and get a"}, "familyId": "bmf_b282e90af67a", "firstSeenAt": "2026-09-09", "heat": null, "id": "bm_llm-benchmark-panel_413dbe56", "indexedAt": "2026-09-09T06:18:35.023319Z", "industrySectors": ["Financial Services"], "links": {"code": "https://github.com/yunusbaysal/llm-benchmark-panel", "project": "https://img.shields.io/badge/coverage-87%25-brightgreen"}, "metrics": [], "motivation": "llm-benchmark-panel # LLM Benchmark Panel ![CI](https://github.com/yunusbaysal/llm-benchmark-panel/actions/workflows/ci.yml/badge.svg) ![Coverage](https://img.shields.io/badge/coverage-87%25-brightgreen) ![Python](https://img.shields.io/badge/python-3.10%20%7C%203.11%20%7C%203.12-blue) ![License](https://img.shields.io/badge/license-MIT-green) A multi-provider LLM benchmarking harness: define task suites, run any mi…", "name": "LLM Benchmark Panel", "oneLine": "Multi-provider LLM benchmarking harness with task suites including reasoning, coding, and Turkish-language questions; scoring supports exact_match, keywords, regex, and optional llm_judge.", "paperTitle": "llm-benchmark-panel", "primaryDomain": "Finance", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://github.com/yunusbaysal/llm-benchmark-panel", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-09T06:18:35.023319Z"}, "publications": [], "ranking": {"30d": {"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": 30, "historyDate": "2026-09-05", "rank": null, "score": null, "windowDays": 30}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": 0.0, "value": 0}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 194, "score": 23}, "method": "attention-ranking-v13", "rank": 194, "score": 23}, "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": 0.0, "value": 0}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 458, "score": 23}, "method": "attention-ranking-v13", "rank": 458, "score": 23}}, "readiness": "Runnable", "recognitionConfidence": 0.4, "relation": "unclear", "releasedAt": "2026-09-08", "source": {"authors": ["yunusbaysal"], "categories": [], "id": "github:yunusbaysal/llm-benchmark-panel", "publicSignals": {"githubStars": 0}, "title": "llm-benchmark-panel", "type": "github", "url": "https://github.com/yunusbaysal/llm-benchmark-panel"}, "sourceUpdatedAt": "2026-09-08T21:03:36Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Provides an open-source, offline-capable harness for comparing model accuracy, latency, and cost across providers, with reproducible mock models and static dashboards."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
