Creative Writing Evaluation on EQ-Bench Creative Writing v3
83.8EQ-BenchGPT-4o
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-4o2026.04 | 83.8 | |
| Claude 3 Opus2026.04 | 82.88 | |
| Claude Sonnet 3.52026.04 | 82.04 | |
| New Yorker (professional)status=professional2026.04 | 78.71 | |
| Tell Me a Story (amateur)status=amateur2026.04 | 60.89 | |
| StoryStar (amateur)status=amateur2026.04 | 45.81 |