{"source":"preview","reason":"query_failed","publishedAt":"2026-08-15T00:00:00.000Z","publishedClassCount":0,"publication":{"generatedAt":"2026-08-15T00:00:00.000Z","methodologyUrl":"https://hivebase.ai/docs/guides/model-intelligence","workClasses":[{"workClass":"code.agentic","label":"Agentic coding","verdictModelKey":"","verdictHarnessKey":null,"verdict":"No published HiveBase default in this preview snapshot.","rationale":"Layout and methodology preview only. This snapshot does not name a preferred model. Live defaults appear when the public `current` publication exists.","composite":null,"sampleSize":0,"confidenceLower":null,"confidenceUpper":null,"evidence":[{"sourceId":"terminal_bench","sourceLabel":"Terminal-Bench","attributionUrl":"https://www.tbench.ai/","metric":"pass_rate","summary":"Attributed agentic CLI source. Numbers stay on the source.","redistributable":true},{"sourceId":"swe_rebench","sourceLabel":"SWE-Rebench","attributionUrl":"https://huggingface.co/datasets/nebius/SWE-rebench-leaderboard","metric":"tasks","summary":"The public Hugging Face dataset is evaluation tasks, not a model-score feed.","redistributable":true},{"sourceId":"aa_coding_index","sourceLabel":"AA Coding Index","attributionUrl":"https://artificialanalysis.ai/models?intelligence=coding-index","metric":"score","summary":"Tracked internally — see artificialanalysis.ai","redistributable":false}],"defaultKind":"unpublished","applicableTasks":["Multi-file repository work: implement, recover, verify. Ranked as (harness, model, role)."],"limitations":["Research-based defaults stay useful before HiveBase outcome data accumulates.","Outcome statistics are observational HiveBase-owned dogfood, not a causal ranking.","The same model in a different harness is a different row.","Artificial Analysis numbers are tracked internally and never rehosted."],"researchBasis":{"summary":"Preview methodology only. Not a live research-based default.","citations":[{"sourceId":"terminal_bench","sourceLabel":"Terminal-Bench","attributionUrl":"https://www.tbench.ai/"},{"sourceId":"swe_rebench","sourceLabel":"SWE-Rebench","attributionUrl":"https://huggingface.co/datasets/nebius/SWE-rebench-leaderboard"},{"sourceId":"aa_coding_index","sourceLabel":"AA Coding Index","attributionUrl":"https://artificialanalysis.ai/models?intelligence=coding-index"}],"freshnessAt":null},"outcomeStats":null,"servingModelKey":"","servingHarnessKey":null,"servingState":null,"servingCanaryPercent":null},{"workClass":"code.frontend","label":"Front-end / UI","verdictModelKey":"","verdictHarnessKey":null,"verdict":"No published HiveBase default in this preview snapshot.","rationale":"Layout and methodology preview only. This snapshot does not name a preferred model. Live defaults appear when the public `current` publication exists.","composite":null,"sampleSize":0,"confidenceLower":null,"confidenceUpper":null,"evidence":[{"sourceId":"design_arena","sourceLabel":"Design Arena","attributionUrl":"https://www.designarena.ai/","metric":"elo","summary":"Blind human Elo on generated UI — attributed, not mirrored. Official API is optional at launch.","redistributable":true},{"sourceId":"lmarena_webdev","sourceLabel":"LMArena WebDev","attributionUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","metric":"rating","summary":"Human preference on web artifacts. See the dataset card.","redistributable":true}],"defaultKind":"unpublished","applicableTasks":["Generated websites, components, and full-stack UI. Taste plus deployable quality."],"limitations":["Research-based defaults stay useful before HiveBase outcome data accumulates.","Outcome statistics are observational HiveBase-owned dogfood, not a causal ranking.","The same model in a different harness is a different row.","Artificial Analysis numbers are tracked internally and never rehosted."],"researchBasis":{"summary":"Preview methodology only. Not a live research-based default.","citations":[{"sourceId":"design_arena","sourceLabel":"Design Arena","attributionUrl":"https://www.designarena.ai/"},{"sourceId":"lmarena_webdev","sourceLabel":"LMArena WebDev","attributionUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset"}],"freshnessAt":null},"outcomeStats":null,"servingModelKey":"","servingHarnessKey":null,"servingState":null,"servingCanaryPercent":null},{"workClass":"code.review","label":"Code review","verdictModelKey":"","verdictHarnessKey":null,"verdict":"No published HiveBase default in this preview snapshot.","rationale":"Layout and methodology preview only. This snapshot does not name a preferred model. Live defaults appear when the public `current` publication exists.","composite":null,"sampleSize":0,"confidenceLower":null,"confidenceUpper":null,"evidence":[{"sourceId":"endor_league","sourceLabel":"Endor Agent Security League","attributionUrl":"https://www.endorlabs.com/","metric":"security","summary":"Attributed security-correctness source for harness × model interaction.","redistributable":true}],"defaultKind":"unpublished","applicableTasks":["Finding real defects without comment fatigue. Cross-family review is required."],"limitations":["Research-based defaults stay useful before HiveBase outcome data accumulates.","Outcome statistics are observational HiveBase-owned dogfood, not a causal ranking.","The same model in a different harness is a different row.","Artificial Analysis numbers are tracked internally and never rehosted."],"researchBasis":{"summary":"Preview methodology only. Not a live research-based default.","citations":[{"sourceId":"endor_league","sourceLabel":"Endor Agent Security League","attributionUrl":"https://www.endorlabs.com/"}],"freshnessAt":null},"outcomeStats":null,"servingModelKey":"","servingHarnessKey":null,"servingState":null,"servingCanaryPercent":null},{"workClass":"reasoning.deep","label":"Deep reasoning","verdictModelKey":"","verdictHarnessKey":null,"verdict":"No published HiveBase default in this preview snapshot.","rationale":"Layout and methodology preview only. This snapshot does not name a preferred model. Live defaults appear when the public `current` publication exists.","composite":null,"sampleSize":0,"confidenceLower":null,"confidenceUpper":null,"evidence":[{"sourceId":"epoch_eci","sourceLabel":"Epoch Capabilities Index","attributionUrl":"https://epoch.ai/","metric":"eci","summary":"Versioned contextual evidence — attributed, not mirrored.","redistributable":true},{"sourceId":"aa_intelligence_index","sourceLabel":"AA Intelligence Index","attributionUrl":"https://artificialanalysis.ai/","metric":"score","summary":"Tracked internally — see artificialanalysis.ai","redistributable":false}],"defaultKind":"unpublished","applicableTasks":["Strategic, second-order, long-horizon analysis."],"limitations":["Research-based defaults stay useful before HiveBase outcome data accumulates.","Outcome statistics are observational HiveBase-owned dogfood, not a causal ranking.","Artificial Analysis numbers are tracked internally and never rehosted."],"researchBasis":{"summary":"Preview methodology only. Not a live research-based default.","citations":[{"sourceId":"epoch_eci","sourceLabel":"Epoch Capabilities Index","attributionUrl":"https://epoch.ai/"},{"sourceId":"aa_intelligence_index","sourceLabel":"AA Intelligence Index","attributionUrl":"https://artificialanalysis.ai/"}],"freshnessAt":null},"outcomeStats":null,"servingModelKey":"","servingHarnessKey":null,"servingState":null,"servingCanaryPercent":null},{"workClass":"agentic.tools","label":"Agentic tool use","verdictModelKey":"","verdictHarnessKey":null,"verdict":"No published HiveBase default in this preview snapshot.","rationale":"Layout and methodology preview only. This snapshot does not name a preferred model. Live defaults appear when the public `current` publication exists.","composite":null,"sampleSize":0,"confidenceLower":null,"confidenceUpper":null,"evidence":[{"sourceId":"bfcl","sourceLabel":"Berkeley Function Calling Leaderboard","attributionUrl":"https://gorilla.cs.berkeley.edu/leaderboard.html","metric":"accuracy","summary":"Attributed function-calling source.","redistributable":true},{"sourceId":"lmarena_agent","sourceLabel":"LMArena Agent","attributionUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","metric":"ips_score","summary":"Official agent IPS schema, separate from text/vision/webdev ratings.","redistributable":true}],"defaultKind":"unpublished","applicableTasks":["Multi-step tool calling with schema fidelity and recovery."],"limitations":["Research-based defaults stay useful before HiveBase outcome data accumulates.","Outcome statistics are observational HiveBase-owned dogfood, not a causal ranking.","Artificial Analysis numbers are tracked internally and never rehosted."],"researchBasis":{"summary":"Preview methodology only. Not a live research-based default.","citations":[{"sourceId":"bfcl","sourceLabel":"Berkeley Function Calling Leaderboard","attributionUrl":"https://gorilla.cs.berkeley.edu/leaderboard.html"},{"sourceId":"lmarena_agent","sourceLabel":"LMArena Agent","attributionUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset"}],"freshnessAt":null},"outcomeStats":null,"servingModelKey":"","servingHarnessKey":null,"servingState":null,"servingCanaryPercent":null},{"workClass":"writing.narrative","label":"Long-form writing","verdictModelKey":"","verdictHarnessKey":null,"verdict":"No published HiveBase default in this preview snapshot.","rationale":"Layout and methodology preview only. This snapshot does not name a preferred model. Live defaults appear when the public `current` publication exists.","composite":null,"sampleSize":0,"confidenceLower":null,"confidenceUpper":null,"evidence":[{"sourceId":"lmarena_text","sourceLabel":"LMArena Text","attributionUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","metric":"rating","summary":"Human preference on text. See the dataset card.","redistributable":true}],"defaultKind":"unpublished","applicableTasks":["User-visible prose, brand voice, and durable narratives."],"limitations":["Research-based defaults stay useful before HiveBase outcome data accumulates.","Outcome statistics are observational HiveBase-owned dogfood, not a causal ranking.","Artificial Analysis numbers are tracked internally and never rehosted."],"researchBasis":{"summary":"Preview methodology only. Not a live research-based default.","citations":[{"sourceId":"lmarena_text","sourceLabel":"LMArena Text","attributionUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset"}],"freshnessAt":null},"outcomeStats":null,"servingModelKey":"","servingHarnessKey":null,"servingState":null,"servingCanaryPercent":null},{"workClass":"extraction.structured","label":"Structured extraction","verdictModelKey":"","verdictHarnessKey":null,"verdict":"No published HiveBase default in this preview snapshot.","rationale":"Layout and methodology preview only. This snapshot does not name a preferred model. Live defaults appear when the public `current` publication exists.","composite":null,"sampleSize":0,"confidenceLower":null,"confidenceUpper":null,"evidence":[{"sourceId":"aa_intelligence_index","sourceLabel":"AA Intelligence Index","attributionUrl":"https://artificialanalysis.ai/","metric":"score","summary":"Tracked internally — see artificialanalysis.ai","redistributable":false}],"defaultKind":"unpublished","applicableTasks":["Schema-valid JSON / Output.object without silent field loss."],"limitations":["Research-based defaults stay useful before HiveBase outcome data accumulates.","Outcome statistics are observational HiveBase-owned dogfood, not a causal ranking.","Artificial Analysis numbers are tracked internally and never rehosted."],"researchBasis":{"summary":"Preview methodology only. Not a live research-based default.","citations":[{"sourceId":"aa_intelligence_index","sourceLabel":"AA Intelligence Index","attributionUrl":"https://artificialanalysis.ai/"}],"freshnessAt":null},"outcomeStats":null,"servingModelKey":"","servingHarnessKey":null,"servingState":null,"servingCanaryPercent":null},{"workClass":"longctx","label":"Long context","verdictModelKey":"","verdictHarnessKey":null,"verdict":"No published HiveBase default in this preview snapshot.","rationale":"Layout and methodology preview only. This snapshot does not name a preferred model. Live defaults appear when the public `current` publication exists.","composite":null,"sampleSize":0,"confidenceLower":null,"confidenceUpper":null,"evidence":[{"sourceId":"aa_lcr","sourceLabel":"AA Long-Context Reasoning","attributionUrl":"https://artificialanalysis.ai/","metric":"score","summary":"Tracked internally — see artificialanalysis.ai","redistributable":false}],"defaultKind":"unpublished","applicableTasks":["Documents, transcripts, and large codebases. Effective window, not marketed size."],"limitations":["Research-based defaults stay useful before HiveBase outcome data accumulates.","Outcome statistics are observational HiveBase-owned dogfood, not a causal ranking.","Artificial Analysis numbers are tracked internally and never rehosted."],"researchBasis":{"summary":"Preview methodology only. Not a live research-based default.","citations":[{"sourceId":"aa_lcr","sourceLabel":"AA Long-Context Reasoning","attributionUrl":"https://artificialanalysis.ai/"}],"freshnessAt":null},"outcomeStats":null,"servingModelKey":"","servingHarnessKey":null,"servingState":null,"servingCanaryPercent":null},{"workClass":"vision.doc","label":"Document / vision","verdictModelKey":"","verdictHarnessKey":null,"verdict":"No published HiveBase default in this preview snapshot.","rationale":"Layout and methodology preview only. This snapshot does not name a preferred model. Live defaults appear when the public `current` publication exists.","composite":null,"sampleSize":0,"confidenceLower":null,"confidenceUpper":null,"evidence":[{"sourceId":"lmarena_vision","sourceLabel":"LMArena Vision","attributionUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","metric":"rating","summary":"Human preference on vision tasks. See the dataset card.","redistributable":true}],"defaultKind":"unpublished","applicableTasks":["PDF, OCR, diagram, and image understanding."],"limitations":["Research-based defaults stay useful before HiveBase outcome data accumulates.","Outcome statistics are observational HiveBase-owned dogfood, not a causal ranking.","Artificial Analysis numbers are tracked internally and never rehosted."],"researchBasis":{"summary":"Preview methodology only. Not a live research-based default.","citations":[{"sourceId":"lmarena_vision","sourceLabel":"LMArena Vision","attributionUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset"}],"freshnessAt":null},"outcomeStats":null,"servingModelKey":"","servingHarnessKey":null,"servingState":null,"servingCanaryPercent":null},{"workClass":"speed.classify","label":"Classification / gates","verdictModelKey":"","verdictHarnessKey":null,"verdict":"No published HiveBase default in this preview snapshot.","rationale":"Layout and methodology preview only. This snapshot does not name a preferred model. Live defaults appear when the public `current` publication exists.","composite":null,"sampleSize":0,"confidenceLower":null,"confidenceUpper":null,"evidence":[],"defaultKind":"unpublished","applicableTasks":["Binary and cheap structured gates. Recoverable if wrong."],"limitations":["Research-based defaults stay useful before HiveBase outcome data accumulates.","Outcome statistics are observational HiveBase-owned dogfood, not a causal ranking.","Artificial Analysis numbers are tracked internally and never rehosted."],"researchBasis":{"summary":"Preview methodology only. Not a live research-based default.","citations":[],"freshnessAt":null},"outcomeStats":null,"servingModelKey":"","servingHarnessKey":null,"servingState":null,"servingCanaryPercent":null},{"workClass":"intel.x","label":"X / community intel","verdictModelKey":"","verdictHarnessKey":null,"verdict":"No published HiveBase default in this preview snapshot.","rationale":"Layout and methodology preview only. This snapshot does not name a preferred model. Live defaults appear when the public `current` publication exists.","composite":null,"sampleSize":0,"confidenceLower":null,"confidenceUpper":null,"evidence":[],"defaultKind":"unpublished","applicableTasks":["Native X search and community recency. Discovery, not deciding."],"limitations":["Research-based defaults stay useful before HiveBase outcome data accumulates.","Outcome statistics are observational HiveBase-owned dogfood, not a causal ranking.","Artificial Analysis numbers are tracked internally and never rehosted."],"researchBasis":{"summary":"Preview methodology only. Not a live research-based default.","citations":[],"freshnessAt":null},"outcomeStats":null,"servingModelKey":"","servingHarnessKey":null,"servingState":null,"servingCanaryPercent":null}],"changelog":[{"occurredAt":"2026-08-15T00:00:00.000Z","eventType":"hivebase_index_run","summary":"Preview snapshot for hivebase.ai/models layout. Not a live production index and not a preferred-model list."},{"occurredAt":"2026-08-12T09:10:00.000Z","eventType":"auto_revert","summary":"Example auto-revert event type the live changelog can show. This preview row is not a recorded production revert."},{"occurredAt":"2026-08-10T12:00:00.000Z","eventType":"source_stale","summary":"SWE-bench Verified remains weight-zero (saturated / contaminated) and is not used for fusion."}],"lastRefreshBySource":[{"sourceId":"first_party","finishedAt":null,"status":"skipped"},{"sourceId":"artificial_analysis","finishedAt":null,"status":"skipped"},{"sourceId":"openrouter","finishedAt":null,"status":"skipped"}],"notes":[]}}