benchmark evidence
EQ-Bench Creative Writing v3
Pairwise creative writing quality benchmark. Rubric score 0-100; higher means more creative and stylistically rich prose.
winner on EQ-Bench Creative Writing v3
OpenAI: GPT-5.585.0
direct benchmark result, not a broad vertical composite | source row dated 2000-01-01
scored on 2000-01-01 · stale source data (9646d)
latest mapped results | top 20
| # | Model | Score | Evidence | Tested |
|---|---|---|---|---|
| 1 | OpenAI: GPT-5.5 | 85.0 | model-only independent_benchmark | 2000-01-01 |
| 2 | OpenAI: GPT-5.4 | 84.5 | model-only independent_benchmark | 2000-01-01 |
| 3 | OpenAI: GPT-5 | 84.0 | model-only independent_benchmark | 2000-01-01 |
| 4 | OpenAI: GPT-5.2 | 83.3 | model-only independent_benchmark | 2000-01-01 |
| 5 | Anthropic: Claude Opus 4.6 | 82.7 | model-only independent_benchmark | 2000-01-01 |
| 6 | OpenAI: GPT-5.4 Mini | 82.5 | model-only independent_benchmark | 2000-01-01 |
| 7 | MoonshotAI: Kimi K2 Thinking | 82.3 | model-only independent_benchmark | 2000-01-01 |
| 8 | DeepSeek: DeepSeek V4 Pro | 82.3 | model-only independent_benchmark | 2000-01-01 |
| 9 | Anthropic: Claude Opus 4.5 | 81.8 | model-only independent_benchmark | 2000-01-01 |
| 10 | DeepSeek: DeepSeek V4 Flash | 81.5 | model-only independent_benchmark | 2000-01-01 |
| 11 | DeepSeek: DeepSeek V3.2 | 81.4 | model-only independent_benchmark | 2000-01-01 |
| 12 | OpenAI: o3 | 81.4 | model-only independent_benchmark | 2000-01-01 |
| 13 | Anthropic: Claude Sonnet 4.5 | 80.7 | model-only independent_benchmark | 2000-01-01 |
| 14 | Anthropic: Claude Opus 4.7 | 80.3 | model-only independent_benchmark | 2000-01-01 |
| 15 | OpenAI: GPT-4.1 | 79.0 | model-only independent_benchmark | 2000-01-01 |
| 16 | Anthropic: Claude Sonnet 4.6 | 78.8 | model-only independent_benchmark | 2000-01-01 |
| 17 | DeepSeek: R1 | 78.4 | model-only independent_benchmark | 2000-01-01 |
| 18 | Google: Gemma 3 27B | 76.7 | model-only independent_benchmark | 2000-01-01 |
| 19 | Google: Gemini 2.0 Flash | 71.2 | model-only independent_benchmark | 2000-01-01 |
what this result means
Pairwise creative writing quality benchmark. Rubric score 0-100; higher means more creative and stylistically rich prose.
This benchmark contributes direct public evidence. Read its scope before generalizing the result.
A win here is a win on EQ-Bench Creative Writing v3. Broad task pages require independent corroboration before naming a general winner.
source record
category: eq
metric: accuracy
matched models: 19
latest source date: 2000-01-01
direction: higher is better