{"record": {"aliases": [], "artifacts": [{"id": "gh:ajbermudezh22/agent-model-bench", "kind": "repo", "url": "https://github.com/ajbermudezh22/agent-model-bench"}, {"kind": "website", "url": "https://ajbermudezh22.github.io/agent-model-bench/"}], "categories": ["Agents", "General AI", "Language & Knowledge"], "description": {"en": "Evaluates language models on tool calling and strict JSON adherence using 32 cases, scoring exact tool and argument matches and JSON parsing with strict and content-based criteria."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://github.com/ajbermudezh22/agent-model-bench", "source": "claire_radar", "source_url": "https://github.com/ajbermudezh22/agent-model-bench", "title": "agent-model-bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:github:ajbermudezh22/agent-model-bench", "modality": null, "name": "agent-model-bench", "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_agent-model-bench_4106c088", "origin_source": "github", "recognition_confidence": "0.4", "record_sha256": "d1a5666a7ffba87ea2728c2b7c2359d626c08723247af38384e20abb5d02736f", "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/ajbermudezh22/agent-model-bench"}, "publisher": null, "released": "2026-08-21", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:github:ajbermudezh22/agent-model-bench", "source_url": "https://github.com/ajbermudezh22/agent-model-bench"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-github-ajbermudezh22-agent-model-bench", "source": "claire_radar", "source_benchmark_id": "github:ajbermudezh22/agent-model-bench", "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/ajbermudezh22/agent-model-bench", "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 small case count and narrow scope limit visibility, though the focus on tool calling and JSON faithfulness addresses a recognized need in agent frameworks.", "score": 35}, "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": "9e921b5a1165c6183814bf60f81844bba971f83781ac686c60da848da065c65f", "model": "deepseek-v4-pro"}, "curation": {"decisionReason": "The formal benchmark name is source-grounded, but the public release does not yet meet the independent evidence or adoption threshold.", "model": "deepseek-v4-pro", "reviewedAt": "2026-08-25T17:43:56.718736Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-candidate", "demo": false, "description": "Evaluates language models on tool calling and strict JSON adherence using 32 cases, scoring exact tool and argument matches and JSON parsing with strict and content-based criteria.", "discoverySources": [{"id": "github:ajbermudezh22/agent-model-bench", "type": "github", "url": "https://github.com/ajbermudezh22/agent-model-bench"}], "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": "agent-model-bench Which model should power your agent?"}, "familyId": "bmf_edbdc48fb887", "firstSeenAt": "2026-08-22", "heat": null, "id": "bm_agent-model-bench_4106c088", "indexedAt": "2026-08-22T19:19:35.289219Z", "industrySectors": [], "links": {"code": "https://github.com/ajbermudezh22/agent-model-bench", "project": "https://ajbermudezh22.github.io/agent-model-bench/"}, "metrics": [], "motivation": "agent-model-bench Which model should power your agent?", "name": "agent-model-bench", "oneLine": "Evaluates language models on tool calling and strict JSON adherence using 32 cases, scoring exact tool and argument matches and JSON parsing with strict and content-based criteria.", "paperTitle": "agent-model-bench", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://github.com/ajbermudezh22/agent-model-bench", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-22T19:19:35.289219Z"}, "publications": [], "publishers": [{"name": "ajbermudezh22", "organizationType": "community", "role": "benchmark-publisher", "sourceUrl": "https://github.com/ajbermudezh22/agent-model-bench"}], "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": 0.0, "value": 0}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 514, "score": 23}, "method": "attention-ranking-v13", "rank": 514, "score": 23}}, "readiness": "Runnable", "recognitionConfidence": 0.4, "relation": "unclear", "releasedAt": "2026-08-21", "source": {"authors": ["ajbermudezh22"], "categories": [], "id": "github:ajbermudezh22/agent-model-bench", "title": "agent-model-bench", "type": "github", "url": "https://github.com/ajbermudezh22/agent-model-bench"}, "sourceUpdatedAt": "2026-08-21T12:42:23Z", "topics": ["Agents"], "venueAttempts": [], "whyItMatters": "Offers a small, honest screen for agent-critical capabilities, exposing formatting discipline differences that practical JSON parsing would penalize."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
