Benchmarks · creative
EQ-Bench Creative Writing v3
A LLM-judged creative writing benchmark with vocabulary and GPT-slop controls. Maintained by EQ-bench. Score: Elo Score column in the leaderboard.
111 models · 111 results · data as of 2026-11-06 · eqbench.com ↗
Leaderboard
GPT-6 Astra max
All results
111 rows| # | Model | Effort | Score |
|---|---|---|---|
| 1 | GPT-6 Astra | max | 2177 |
| 2 | Kimi K3.1 | max | 2173 |
| 3 | Fable 5.1 | max | 2155 |
| 4 | Opus 5 | max | 2135 |
| 5 | GPT-6 Sol | max | 2126 |
| 6 | Kimi K3 | max | 2083 |
| 7 | GLM 5.3 | max | 2076 |
| 8 | Opus 5.5 | max | 2051 |
| 9 | Grok 4.7 | max | 2012 |
| 10 | GPT-5.6 Sol | max | 1974 |
| 11 | Fable 5 | max | 1944 |
| 12 | Muse Spark 1.1 | max | 1928 |
| 13 | Opus 4.7 | max | 1915 |
| 14 | Muse Spark 1.3 | max | 1907 |
| 15 | GPT-5.6 Terra | max | 1856 |
| 16 | GPT-5.5 | xhigh | 1845 |
| 17 | Qwen 3.8 | xhigh | 1844 |
| 18 | Muse Spark 1.2 | max | 1842 |
| 19 | GPT-5.4 | xhigh | 1841 |
| 20 | Opus 4.8 | max | 1840 |
| 21 | GPT-5.6 Luna | max | 1832 |
| 22 | Sonnet 4.6 | max | 1811 |
| 23 | Opus 4.6 | max | 1810 |
| 24 | Sonnet 5 | max | 1798 |
| 25 | GLM 5.2 | max | 1759 |
| 26 | Gemini 4 Argon | max | 1758 |
| 27 | Gemini 3.8 Flash | max | 1744 |
| 28 | Kimi K2.6 | max | 1721 |
| 29 | Gemini 3.7 Flash | max | 1720 |
| 30 | GPT-5.2 | xhigh | 1703 |