Updated daily at 05:00 UTC
Benchmark
EQ-Bench Longform Creative Writing
Measures: From a minimal prompt, the model plans a novella, revises the plan and writes it in 8 turns of about 1,000 words. Claude Sonnet 4.6 scores each chapter and the whole piece on a 14-criterion rubric, giving 0-100. Forced metaphor is weighted up, and a penalty applies when quality degrades over length.
- Maintainer
- Sam Paech (EQ-Bench)
- Introduced
- 2025
- Status
- Active
- Saturation
- Near-ceiling
- Typical provenance
- Independent
- In scoring set
- Yes
Leaderboard
Independent and third-party results only.
No independent or third-party results yet. Show all results