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 | ||
|---|---|---|---|---|
| Claude Sonnet 4.5 | 87% | $0.045 | 39.5s | |
| Claude Sonnet 4.6 | 87% | $0.040 | 37.2s | |
| Writer: Palmyra X5 | 84% | $0.013 | 22.1s | |
| Z.AI GLM 5 | 83% | $0.0095 | 1.5m | |
| DeepSeek V3 (2024-12-26) | 78% | $0.0029 | 35.6s | |
| Qwen 3.5 397B A17B | 84% | $0.0048 | 3.3m | |
| GPT-4.1 | 80% | $0.021 | 40.8s | |
| GPT-5.1 | 86% | $0.053 | 1.8m | |
| DeepSeek-V2 Chat | 78% | $0.0029 | 42.0s | |
| Rocinante 12B | 79% | $0.0018 | 23.4s | |
| Ministral 3 14B | 76% | $0.0013 | 9.5s | |
| o4 Mini | 79% | $0.019 | 34.0s | |
| DeepSeek V3.2 | 79% | $0.0022 | 1.1m | |
| Grok 4,1 Fast | 78% | $0.0024 | 50.4s | |
| Gemini 2.5 Flash | 77% | $0.0057 | 10.6s | |
| Hermes 3 70B | 79% | $0.0021 | 2.0m | |
| DeepSeek V3 (2025-03-24) | 78% | $0.0017 | 30.2s | |
| Claude Opus 4.6 | 86% | $0.087 | 1.1m | |
| Z.AI GLM 4.7 | 78% | $0.011 | 1.3m | |
| Claude Opus 4.5 | 83% | $0.079 | 48.4s | |
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 | 86% | 98% | 85% | |
| Claude Sonnet 4.6 | 87% | 96% | 84% | |
| Claude Sonnet 4.5 | 87% | 94% | 83% | |
| Claude Opus 4.6 | 86% | 96% | 82% | |
| Qwen 3.5 397B A17B | 84% | 94% | 81% | |
| GPT-5 | 85% | 95% | 80% | |
| Gemini 3.1 Pro (Preview) | 83% | 93% | 78% | |
| Claude Opus 4.5 | 83% | 91% | 77% | |
| o4 Mini | 79% | 96% | 77% | |
| Claude Opus 4 | 84% | 90% | 76% | |
| Grok 4,1 Fast | 78% | 98% | 76% | |
| GPT-4.1 | 80% | 93% | 76% | |
| Writer: Palmyra X5 | 84% | 91% | 76% | |
| GPT-5.2 | 78% | 95% | 75% | |
| Gemini 3 Pro (Preview) | 77% | 97% | 74% | |
| DeepSeek V3.2 | 79% | 94% | 74% | |
| Gemma 3 27B | 77% | 97% | 74% | |
| Z.AI GLM 5 | 83% | 89% | 74% | |
| WizardLM 2 8x22b | 77% | 96% | 73% | |
| DeepSeek V3 (2024-12-26) | 78% | 91% | 73% | |
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 | ||
|---|---|---|---|---|---|
| Claude Sonnet 4.6 | 87% | $0.040 | 37.2s | 84% | |
| Claude Sonnet 4.5 | 87% | $0.045 | 39.5s | 83% | |
| GPT-5.1 | 86% | $0.053 | 1.8m | 85% | |
| Claude Opus 4.6 | 86% | $0.087 | 1.1m | 82% | |
| Writer: Palmyra X5 | 84% | $0.013 | 22.1s | 76% | |
| Qwen 3.5 397B A17B | 84% | $0.0048 | 3.3m | 81% | |
| o4 Mini | 79% | $0.019 | 34.0s | 77% | |
| GPT-4.1 | 80% | $0.021 | 40.8s | 76% | |
| Claude Opus 4.5 | 83% | $0.079 | 48.4s | 77% | |
| Z.AI GLM 5 | 83% | $0.0095 | 1.5m | 74% | |
| Grok 4,1 Fast | 78% | $0.0024 | 50.4s | 76% | |
| DeepSeek V3.2 | 79% | $0.0022 | 1.1m | 74% | |
| GPT-5 | 85% | $0.064 | 3.0m | 80% | |
| Gemma 3 27B | 77% | $0.0010 | 45.9s | 74% | |
| DeepSeek V3 (2024-12-26) | 78% | $0.0029 | 35.6s | 73% | |
| Gemini 2.5 Flash | 77% | $0.0057 | 10.6s | 72% | |
| DeepSeek V3 (2025-03-24) | 78% | $0.0017 | 30.2s | 71% | |
| Rocinante 12B | 79% | $0.0018 | 23.4s | 69% | |
| ByteDance Seed 1.6 Flash | 76% | $0.0015 | 30.1s | 72% | |
| Ministral 3 14B | 76% | $0.0013 | 9.5s | 70% | |