TestsBenchmarks · writing
EQ-Bench Creative Writing v3 (Elo)
LLM-judged (Claude Sonnet 4.6) pairwise Elo on 32 creative-writing prompts x3 with anti-slop/length controls.
Elo ratingHigher is betterCounts toward:Weights: Writing & creativity ×0.7The test's websiteOfficial page ↗
Measured by independent testersIndependent Reported by the makerVendor-reported
| Thinking levelSetting | |||||||
|---|---|---|---|---|---|---|---|
| 1 | GPT-6 Astra | OpenAI | 2173 | Default*gpt-6-astra | Independent testIndependentEQ-Bench ↗ | — | 1 Oct 2026 |
| 2 | Claude Fable 5.1 | Anthropic | 2162 | Default*claude-fable-5-1 | Independent testIndependentEQ-Bench ↗ | — | 1 Oct 2026 |
| 3 | Claude Opus 5 | Anthropic | 2133 | Defaultclaude-opus-5 | Independent testIndependentEQ-Bench ↗ | — | 1 Oct 2026 |
| 4 | GPT-6 Sol | OpenAI | 2125 | Default*gpt-6-sol | Independent testIndependentEQ-Bench ↗ | — | 1 Oct 2026 |
| 5 | Kimi K3 | Moonshot AI (Kimi) | 2082 | Defaultkimi-k3 | Independent testIndependentEQ-Bench ↗ | — | 1 Oct 2026 |
| 6 | GLM-5.3 | Z.ai (Zhipu) | 2075 | DefaultGLM-5.3 | Independent testIndependentEQ-Bench ↗ | — | 1 Oct 2026 |
| 7 | Claude Opus 5.5 | Anthropic | 2050 | Default*claude-opus-5-5 | Independent testIndependentEQ-Bench ↗ | — | 1 Oct 2026 |
| 8 | Grok 4.7 | SpaceXAI (formerly xAI) | 2007 | Default*grok-4.7 | Independent testIndependentEQ-Bench ↗ | — | 1 Oct 2026 |
| 9 | GPT-5.6 Sol | OpenAI | 1972 | Defaultgpt-5.6-sol | Independent testIndependentEQ-Bench ↗ | — | 1 Oct 2026 |
| 10 | Claude Fable 5 | Anthropic | 1943 | Defaultclaude-fable-5 | Independent testIndependentEQ-Bench ↗ | — | 1 Oct 2026 |
| 11 | Aion 3.5 | AionLabs | 1929 | Default*aion-3.5 | Independent testIndependentEQ-Bench ↗ | — | 1 Oct 2026 |
| 12 | Muse Spark 1.1 | Meta (Meta Superintelligence Labs, Muse) | 1927 | Defaultmuse-spark-1.1 | Independent testIndependentEQ-Bench ↗ | — | 1 Oct 2026 |
| 13 | Claude Opus 4.7 | Anthropic | 1914 | Defaultclaude-opus-4-7 | Independent testIndependentEQ-Bench ↗ | — | 1 Oct 2026 |
| 14 | Muse Spark 1.3 | Meta (Meta Superintelligence Labs, Muse) | 1906 | Default*muse-spark-1.3 | Independent testIndependentEQ-Bench ↗ | — | 1 Oct 2026 |
| 15 | GPT-5.6 Terra | OpenAI | 1855 | Defaultgpt-5.6-terra | Independent testIndependentEQ-Bench ↗ | — | 1 Oct 2026 |
| 16 | GPT-5.5 | OpenAI | 1844 | Defaultgpt-5.5 | Independent testIndependentEQ-Bench ↗ | — | 1 Oct 2026 |
| 17 | Qwen3.8 2.4T A95B (open weights) | Qwen (Alibaba) | 1843 | DefaultQwen/Qwen3.8-2.4T-A95B | Independent testIndependentEQ-Bench ↗ | — | 1 Oct 2026 |
| 18 | Muse Spark 1.2 | Meta (Meta Superintelligence Labs, Muse) | 1840 | Defaultmuse-spark-1.2 | Independent testIndependentEQ-Bench ↗ | — | 1 Oct 2026 |
| 19 | Claude Opus 4.8 | Anthropic | 1840 | Defaultclaude-opus-4-8 | Independent testIndependentEQ-Bench ↗ | — | 1 Oct 2026 |
| 20 | GPT-5.4 | OpenAI | 1840 | Defaultgpt-5.4 | Independent testIndependentEQ-Bench ↗ | — | 1 Oct 2026 |
| 21 | GPT-5.6 Luna | OpenAI | 1829 | Defaultgpt-5.6-luna | Independent testIndependentEQ-Bench ↗ | — | 1 Oct 2026 |
| 22 | Claude Sonnet 4.6 | Anthropic | 1810 | Defaultclaude-sonnet-4-6 | Independent testIndependentEQ-Bench ↗ | — | 1 Oct 2026 |
| 23 | Claude Opus 4.6 | Anthropic | 1809 | Defaultclaude-opus-4-6 | Independent testIndependentEQ-Bench ↗ | — | 1 Oct 2026 |
| 24 | Muse Glimmer 30B | Meta (Meta Superintelligence Labs, Muse) | 1798 | Defaultmeta-models/Muse-Glimmer-30B | Independent testIndependentEQ-Bench ↗ | — | 1 Oct 2026 |
| 25 | Claude Sonnet 5 | Anthropic | 1794 | Defaultclaude-sonnet-5 | Independent testIndependentEQ-Bench ↗ | — | 1 Oct 2026 |
| 26 | GLM-5.2 | Z.ai (Zhipu) | 1757 | Defaultzai-org/GLM-5.2 | Independent testIndependentEQ-Bench ↗ | — | 1 Oct 2026 |
| 27 | Gemini 3.8 Flash | Google (Gemini / DeepMind) | 1748 | Default*gemini-3.8-flash | Independent testIndependentEQ-Bench ↗ | — | 1 Oct 2026 |
| 28 | Kimi K2.6 | Moonshot AI (Kimi) | 1725 | Defaultmoonshotai/Kimi-K2.6 | Independent testIndependentEQ-Bench ↗ | — | 1 Oct 2026 |
| 29 | Gemini 3.7 Flash | Google (Gemini / DeepMind) | 1723 | Defaultgemini-3.7-flash | Independent testIndependentEQ-Bench ↗ | — | 1 Oct 2026 |
| 30 | Nemotron 3 Ultra | NVIDIA | 1692 | Defaultnvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4 | Independent testIndependentEQ-Bench ↗ | — | 1 Oct 2026 |
| 31 | Qwen3.8 27B | Qwen (Alibaba) | 1671 | DefaultQwen/Qwen3.8-27B | Independent testIndependentEQ-Bench ↗ | — | 1 Oct 2026 |