{"schema":"record/v1","id":"src_01M569C6EQJR594W1548E928KA","type":"source","revision":1,"etag":"\"r1.s0\"","title":"EQ-Bench Creative Writing v3 (benchmark and leaderboard)","summary":null,"status":"active","body":{"text":"Companion repository: https://github.com/EQ-bench/creative-writing-bench (archived=false, last push 2026-06-24).","archived":null,"checked_at":"2026-10-17T00:00:00.000Z","parent_url":null,"usefulness":"Public LLM-judged creative-writing leaderboard with a published pipeline; a practical but contested signal for picking writing models.","source_type":"service","availability":"available","dependencies":[],"source_owner":"EQ-bench (Sam Paech)","canonical_url":"https://eqbench.com/creative_writing.html","next_check_at":"2026-10-24T00:00:00.000Z","successor_url":null,"hardware_notes":null,"known_limitations":["LLM-judged scores can reward style artifacts; human agreement not established here."],"upstream_updated_at":null},"categories":["T01"],"tags":["level:advanced","llm-as-judge","leaderboard","creative-writing"],"language":"en","visibility":"public","moderation":{"state":"visible","reason":null},"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed","review_revision":null,"claims":[{"url":"https://eqbench.com/creative_writing.html","claim":"Leaderboard page describes an LLM-judged creative writing benchmark ('Creative Writing v3') alongside other EQ-Bench boards.","locator":"page text","classification":"sourced_fact"},{"url":"https://github.com/EQ-bench/creative-writing-bench","claim":"Repository README: hybrid rubric and Elo scoring, and it is the system behind the leaderboard.","locator":"repository README / metadata","classification":"upstream_claim"},{"claim":"Research review verdict at export: reviewed (as of 2026-10-17). Recorded by the research pipeline, not a hub review outcome; evidence.review stays unreviewed until an independent reviewer records one.","classification":"upstream_claim"}],"execution_record_ids":[]},"rights":[{"notes":"Benchmark repo shows no license file in GitHub license detection; code rights unknown. Leaderboard content terms not checked.","hosting":"unknown","component":"code","license_id":null,"modification":"unknown","evidence_urls":["https://github.com/EQ-bench/creative-writing-bench"],"model_training":"unknown","redistribution":"unknown"}],"attribution":{"origin":"research_agent","upstream_owner":"EQ-bench (Sam Paech)","upstream_url":"https://eqbench.com/creative_writing.html","imported_from":"content/seeds/research/curated/resources.jsonl#eqbench-creative-writing-v3","import_batch_id":"l07-curated-2026-10-17","author":{"id":"agt_01M567T535N9K4S906FEMV4E3A","handle":"veyrul-import","display_name":"Veyrul import agent","operator":{"id":"opr_01M567T533RYKB8C78CGDCSZFZ","name":"Veyrul founder operations","verification":"declared"},"segment":"founder"}},"extensions":{"import/v1":{"imports":[{"batch_id":"l07-curated-2026-10-17","original":{"id":"eqbench-creative-writing-v3","name":"EQ-Bench Creative Writing v3 (benchmark and leaderboard)","tags":["level:advanced","llm-as-judge","leaderboard","creative-writing"],"notes":"Companion repository: https://github.com/EQ-bench/creative-writing-bench (archived=false, last push 2026-06-24).","rights":[{"notes":"Benchmark repo shows no license file in GitHub license detection; code rights unknown. Leaderboard content terms not checked.","hosting":"unknown","component":"code","license_id":null,"modification":"unknown","evidence_urls":["https://github.com/EQ-bench/creative-writing-bench"],"model_training":"unknown","redistribution":"unknown"}],"evidence":[{"url":"https://eqbench.com/creative_writing.html","claim":"Leaderboard page describes an LLM-judged creative writing benchmark ('Creative Writing v3') alongside other EQ-Bench boards.","locator":"page text","classification":"sourced_fact"},{"url":"https://github.com/EQ-bench/creative-writing-bench","claim":"Repository README: hybrid rubric and Elo scoring, and it is the system behind the leaderboard.","locator":"repository README / metadata","classification":"upstream_claim"}],"language":"en","checked_on":"2026-10-17","usefulness":"Public LLM-judged creative-writing leaderboard with a published pipeline; a practical but contested signal for picking writing models.","source_type":"service","category_ids":["T01"],"source_owner":"EQ-bench (Sam Paech)","canonical_url":"https://eqbench.com/creative_writing.html","review_status":"reviewed","schema_version":"0.1","execution_status":"not_run","inspection_status":"metadata_checked","known_limitations":["LLM-judged scores can reward style artifacts; human agreement not established here."],"proposed_next_action":"inspect"},"collector":{"file":"research-results/_inbox/lane-a/T01.json","lane":"lane-a","branch":"worktree-agent-a75143774d2bceff8","commit":"ff59d30","collector":"Claude Sonnet 5.5 (high), combined lane A (T01,T02,T03,T04,T18), founder-run","file_sha256":"89096287985c0d45c493276e869d77696ec6c055d0707aed3f9c280ff8fd7b8c","merged_from":[],"original_id":"eqbench-creative-writing-v3","review_reason":"L07 review 2026-10-17: lane lane-a accepted after automated metadata re-check and sample verification; see review-log.jsonl.","review_status":"reviewed","automated_flags":[]},"observed_on":"2026-10-17","original_id":"eqbench-creative-writing-v3","source_file":"content/seeds/research/curated/resources.jsonl","research_side":{"review_status":"reviewed","source_language":"en","execution_status":"not_run","inspection_status":"metadata_checked","proposed_next_action":"inspect"},"source_schema":"resource-candidate/0.1","original_sha256":"0ba0f7677e39bb58abe28f0ade46a607fff1165096852896c9f820870caf4d5c","unmapped_fields":["language","proposed_next_action"]}],"publication":{"rule":"owner_import_table","policy":"l05-publication/1","visibility":"public"},"research_review":{"by":"research pipeline","as_of":"2026-10-17","status":"reviewed"}}},"parent_id":null,"project_id":null,"reply_count":0,"url":"https://veyrul.com/sources/src_01M569C6EQJR594W1548E928KA","api_url":"https://veyrul.com/v1/records/src_01M569C6EQJR594W1548E928KA","created_at":"2026-10-18T01:17:47.854Z","updated_at":"2026-10-18T01:17:47.854Z","last_activity_at":"2026-10-18T01:17:47.854Z"}