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.
Horror: alone in an eerie place at night
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 | ||
|---|---|---|---|---|
| Rocinante 12B | 84% | $0.0006 | 11.9s | |
| Mistral Medium 3.1 | 83% | $0.0030 | 25.4s | |
| Ministral 8B | 81% | $0.0002 | 5.2s | |
| Writer: Palmyra X5 | 84% | $0.010 | 20.4s | |
| Hermes 3 405B | 82% | $0.0020 | 35.8s | |
| Grok 4,1 Fast | 81% | $0.0014 | 31.7s | |
| Qwen 3.5 397B A17B | 86% | $0.0084 | 2.0m | |
| Claude Haiku 4.5 | 81% | $0.0093 | 19.7s | |
| Z.AI GLM 5 | 86% | $0.0061 | 59.0s | |
| DeepSeek V3 (2025-03-24) | 81% | $0.0009 | 46.1s | |
| Llama 3.1 8B | 81% | $0.0003 | 1.2m | |
| Ministral 3 8B | 78% | $0.0003 | 5.2s | |
| Claude 3.5 Haiku | 79% | $0.0022 | 8.8s | |
| ByteDance Seed 1.6 Flash | 81% | $0.0009 | 21.4s | |
| Ministral 3 14B | 78% | $0.0004 | 8.7s | |
| Gemma 3 27B | 81% | $0.0004 | 36.1s | |
| Mistral Large 3 | 82% | $0.0023 | 25.5s | |
| Mistral Small Creative | 80% | $0.0005 | 6.9s | |
| o4 Mini High | 82% | $0.013 | 23.0s | |
| Mistral Large 2 | 78% | $0.0074 | 20.2s | |
Most Stable Models (Top 20)
Ranked by stability (median × consistency). Click a model name to view its detail page.
| Score | Consistency | Stability | ||
|---|---|---|---|---|
| Gemini 3.1 Pro (Preview) | 87% | 99% | 85% | |
| GPT-5.1 | 88% | 95% | 84% | |
| Qwen 3.5 397B A17B | 86% | 95% | 82% | |
| Writer: Palmyra X5 | 84% | 97% | 82% | |
| Z.AI GLM 5 | 86% | 95% | 81% | |
| Mistral Medium 3.1 | 83% | 95% | 80% | |
| Claude Sonnet 4.5 | 86% | 93% | 79% | |
| Cohere Command R+ (Aug. 2024) | 82% | 97% | 79% | |
| GPT-5 | 86% | 92% | 79% | |
| Minimax M2.5 | 83% | 93% | 79% | |
| Claude Haiku 4.5 | 81% | 93% | 78% | |
| Claude Opus 4.6 | 84% | 94% | 78% | |
| GPT-5.2 | 80% | 96% | 78% | |
| Rocinante 12B | 84% | 91% | 78% | |
| Gemini 2.5 Pro | 82% | 94% | 78% | |
| Claude 3.5 Haiku | 79% | 97% | 78% | |
| Claude Opus 4 | 83% | 92% | 78% | |
| Gemma 3 27B | 81% | 97% | 77% | |
| DeepSeek V3 (2025-03-24) | 81% | 94% | 77% | |
| MoonshotAI: Kimi K2.5 | 80% | 97% | 77% | |
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 | ||
|---|---|---|---|---|---|
| Writer: Palmyra X5 | 84% | $0.010 | 20.4s | 82% | |
| Z.AI GLM 5 | 86% | $0.0061 | 59.0s | 81% | |
| Rocinante 12B | 84% | $0.0006 | 11.9s | 78% | |
| Mistral Medium 3.1 | 83% | $0.0030 | 25.4s | 80% | |
| Qwen 3.5 397B A17B | 86% | $0.0084 | 2.0m | 82% | |
| Ministral 8B | 81% | $0.0002 | 5.2s | 76% | |
| Claude Sonnet 4.5 | 86% | $0.029 | 38.6s | 79% | |
| Claude Haiku 4.5 | 81% | $0.0093 | 19.7s | 78% | |
| Claude 3.5 Haiku | 79% | $0.0022 | 8.8s | 78% | |
| Gemma 3 27B | 81% | $0.0004 | 36.1s | 77% | |
| Hermes 3 405B | 82% | $0.0020 | 35.8s | 76% | |
| Mistral Large 3 | 82% | $0.0023 | 25.5s | 76% | |
| ByteDance Seed 1.6 Flash | 81% | $0.0009 | 21.4s | 75% | |
| DeepSeek V3 (2025-03-24) | 81% | $0.0009 | 46.1s | 77% | |
| Grok 4,1 Fast | 81% | $0.0014 | 31.7s | 75% | |
| Cohere Command R+ (Aug. 2024) | 82% | $0.014 | 50.8s | 79% | |
| Mistral Small Creative | 80% | $0.0005 | 6.9s | 74% | |
| GPT-5.1 | 88% | $0.042 | 2.2m | 84% | |
| Minimax M2.5 | 83% | $0.0030 | 1.8m | 79% | |
| o4 Mini High | 82% | $0.013 | 23.0s | 75% | |