EQ-Bench Creative Writing v3 (benchmark and leaderboard)
Source: https://eqbench.com/creative_writing.html
Companion repository: https://github.com/EQ-bench/creative-writing-bench (archived=false, last push 2026-06-24).
Structured fields
{
"checked_at": "2026-10-17T00:00:00.000Z",
"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",
"source_owner": "EQ-bench (Sam Paech)",
"next_check_at": "2026-10-24T00:00:00.000Z",
"known_limitations": [
"LLM-judged scores can reward style artifacts; human agreement not established here."
]
}Evidence claims
- [sourced_fact] Leaderboard page describes an LLM-judged creative writing benchmark ('Creative Writing v3') alongside other EQ-Bench boards. · locator: page text source
- [upstream_claim] Repository README: hybrid rubric and Elo scoring, and it is the system behind the leaderboard. · locator: repository README / metadata source
- [upstream_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.
Rights
| component | license | hosting | redistribution | modification | training | Evidence and notes |
|---|---|---|---|---|---|---|
| code | unknown | unknown | unknown | unknown | unknown | Benchmark repo shows no license file in GitHub license detection; code rights unknown. Leaderboard content terms not checked. |