Bad Writing Habits
Detects common prose quality anti-patterns in AI-generated creative writing, including passive voice, past progressive overuse, weak dialogue tags, filter words, purple prose, cliches, AI-ism words/adverbs/names, and more.
Fantasy: entering an ancient ruin
0-shot Creative writingRule following
Performance Score Distribution (Top 20)
Click a model name to view its detail page.
Price-Performance Score Distribution (Top 20)
Click a model name to view its detail page.
| Score | Cost | Time | ||
|---|---|---|---|---|
| Mistral Small Creative | 78% | $0.0007 | 8.7s | |
| Rocinante 12B | 78% | $0.0010 | 21.7s | |
| ByteDance Seed 1.6 Flash | 79% | $0.0013 | 29.3s | |
| Grok 4,1 Fast | 78% | $0.0018 | 35.4s | |
| Qwen 3.5 397B A17B | 86% | $0.010 | 3.1m | |
| DeepSeek V3 (2025-03-24) | 78% | $0.0013 | 43.2s | |
| Claude Sonnet 4.6 | 79% | $0.027 | 34.0s | |
| GPT-5.1 | 88% | $0.049 | 1.5m | |
| Ministral 3 14B | 76% | $0.0006 | 12.0s | |
| Writer: Palmyra X5 | 78% | $0.011 | 20.8s | |
| o4 Mini High | 81% | $0.025 | 47.7s | |
| Z.AI GLM 5 | 79% | $0.0078 | 1.3m | |
| Mistral Medium 3.1 | 77% | $0.0042 | 23.7s | |
| Llama 3.1 8B | 74% | $0.0002 | 33.0s | |
| Mistral Large | 77% | $0.014 | 38.7s | |
| Gemma 3 4B | 75% | $0.0002 | 18.6s | |
| Mistral Large 3 | 76% | $0.0029 | 34.0s | |
| Hermes 3 405B | 76% | $0.0028 | 42.7s | |
| Minimax M2.5 | 77% | $0.0027 | 41.6s | |
| Mistral Large 2 | 78% | $0.014 | 33.3s | |
Most Stable Models (Top 20)
Ranked by stability (median × consistency). Click a model name to view its detail page.
| Score | Consistency | Stability | ||
|---|---|---|---|---|
| GPT-5.1 | 88% | 97% | 86% | |
| Qwen 3.5 397B A17B | 86% | 96% | 82% | |
| Gemini 3.1 Pro (Preview) | 83% | 98% | 81% | |
| o4 Mini High | 81% | 97% | 79% | |
| GPT-5 | 82% | 93% | 77% | |
| Claude Opus 4.6 | 81% | 94% | 76% | |
| Claude Opus 4.5 | 79% | 94% | 75% | |
| DeepSeek V3 (2025-03-24) | 78% | 95% | 75% | |
| Rocinante 12B | 78% | 95% | 75% | |
| Grok 4,1 Fast | 78% | 94% | 74% | |
| Claude Opus 4 | 77% | 95% | 74% | |
| MoonshotAI: Kimi K2.5 | 77% | 96% | 73% | |
| Claude Sonnet 4.6 | 79% | 90% | 73% | |
| GPT-4.1 | 78% | 94% | 73% | |
| ByteDance Seed 1.6 Flash | 79% | 93% | 73% | |
| Mistral Medium 3.1 | 77% | 95% | 73% | |
| Z.AI GLM 4.7 | 78% | 95% | 72% | |
| Mistral Large | 77% | 93% | 72% | |
| Mistral Large 3 | 76% | 95% | 72% | |
| Writer: Palmyra X5 | 78% | 92% | 72% | |
Top Overall Models (Top 20)
Ranked by composite score (performance, cost, speed & stability). Click a model name to view its detail page.
| Score | Cost | Speed | Stability | ||
|---|---|---|---|---|---|
| GPT-5.1 | 88% | $0.049 | 1.5m | 86% | |
| Rocinante 12B | 78% | $0.0010 | 21.7s | 75% | |
| o4 Mini High | 81% | $0.025 | 47.7s | 79% | |
| Mistral Small Creative | 78% | $0.0007 | 8.7s | 71% | |
| Grok 4,1 Fast | 78% | $0.0018 | 35.4s | 74% | |
| ByteDance Seed 1.6 Flash | 79% | $0.0013 | 29.3s | 73% | |
| DeepSeek V3 (2025-03-24) | 78% | $0.0013 | 43.2s | 75% | |
| Writer: Palmyra X5 | 78% | $0.011 | 20.8s | 72% | |
| Mistral Medium 3.1 | 77% | $0.0042 | 23.7s | 73% | |
| Ministral 3 14B | 76% | $0.0006 | 12.0s | 72% | |
| Gemma 3 4B | 75% | $0.0002 | 18.6s | 71% | |
| Mistral Large 2 | 78% | $0.014 | 33.3s | 71% | |
| Claude Sonnet 4.6 | 79% | $0.027 | 34.0s | 73% | |
| Mistral Large 3 | 76% | $0.0029 | 34.0s | 72% | |
| Mistral Large | 77% | $0.014 | 38.7s | 72% | |
| Qwen 3.5 397B A17B | 86% | $0.010 | 3.1m | 82% | |
| GPT-4.1 | 78% | $0.018 | 49.3s | 73% | |
| Claude Haiku 4.5 | 76% | $0.0097 | 18.3s | 69% | |
| Gemini 2.5 Flash | 73% | $0.0045 | 9.4s | 71% | |
| Z.AI GLM 5 | 79% | $0.0078 | 1.3m | 72% | |