Creative Writing v3 — leaderboard
Creative Writing v3 evaluates model capability on writing tasks from the linked upstream source with Elo score as the primary reported metric.
Metric: Elo score (self-reported). Source: benchmarklist.com. Status: saturation imminent. 102 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.7 | 2215.9 |
| 2 | GPT-5.5 | 2024.3 |
| 3 | GPT-5.4 | 2019.2 |
| 4 | Claude Sonnet 4.6 | 1990.7 |
| 5 | Claude Opus 4.6 | 1964.6 |
| 6 | GPT-5.2 | 1800.3 |
| 7 | Claude Sonnet 4.5 | 1777 |
| 8 | Claude Opus 4.5 | 1769.4 |
| 9 | O3 | 1750.8 |
| 10 | GPT-5.4 Mini | 1726.4 |
| 11 | Kimi K2 (Thinking) | 1698.8 |
| 12 | Grok 4.20 | 1683.7 |
| 13 | GLM-5 | 1663.6 |
| 14 | GPT-5 | 1643.9 |
| 15 | Claude Opus 4 | 1638.1 |
Interactive version: theaggregate.ai/benchmark?slug=creative-writing-v3 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.