Horror: alone in an eerie place at night

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.

Creative Writing Hallucination

Performance Score Distribution (Top 20)

Click a model name to view its detail page.

	Score
Claude Opus 5 (Reasoning, Low)	94%
Claude Opus 5 (Reasoning)	93%
GPT-5.4 (Reasoning)	93%
Claude Opus 5	92%
GPT-5.6 Sol	92%
GPT-5.5 (Reasoning)	92%
Z.AI GLM 5.1	91%
GPT-5.5	91%
GPT-5.6 Sol (Reasoning)	91%
Grok 4.5 (Reasoning, Low)	91%
GPT-5.5 (Reasoning, Low)	91%
GPT-5.6 Terra	91%
GPT-5.6 Terra (Reasoning)	90%
Claude Sonnet 4.6 (Reasoning)	90%
Muse Spark 1.1 (Reasoning, Medium)	90%
GPT-5.4 (Reasoning, Low)	90%
GPT-5.4	90%
GPT-5.4 Mini (Reasoning)	90%
Grok 4.5 (Reasoning, High)	90%
Muse Spark 1.1 (Reasoning, Minimal)	90%

	Score	Cost	Time
Muse Spark 1.1 (Reasoning, Minimal)	90%	$0.012	14.6s
Muse Spark 1.1 (Reasoning, Medium)	90%	$0.015	19.4s
GPT-5.4 Mini (Reasoning)	90%	$0.017	22.1s
Z.AI GLM 5 Turbo	88%	$0.0072	27.5s
Grok 4.5 (Reasoning, Low)	91%	$0.017	44.0s
Z.AI GLM 5.1	91%	$0.014	1.2m
GPT-5.6 Luna	88%	$0.015	14.9s
GPT-5.6 Terra (Reasoning)	90%	$0.038	28.1s
GPT-5.4 Nano (Reasoning, Low)	85%	$0.0045	19.4s
DeepSeek V4 Flash (Reasoning)	86%	$0.0006	28.2s
GPT-5.4 Mini (Reasoning, Low)	88%	$0.013	14.9s
Z.AI GLM 5	88%	$0.0075	50.7s
Gemini 3.5 Flash Lite (Reasoning, Minimal)	85%	$0.0032	4.3s
Qwen3 235B A22B Instruct 2507	87%	$0.0015	48.5s
GPT-5.6 Luna (Reasoning)	88%	$0.016	14.9s
GPT-5.6 Terra	91%	$0.036	28.1s
Gemini 3.5 Flash Lite (Reasoning)	85%	$0.0031	4.1s
GPT-5.4 Mini	86%	$0.014	15.8s
Aion 3.0 Mini	88%	$0.0062	1.1m
Aion 3.0	89%	$0.031	1.0m

	Score	Consistency	Stability
GPT-5.4 (Reasoning)	93%	98%	91%
Claude Opus 5 (Reasoning)	93%	97%	91%
Claude Opus 5 (Reasoning, Low)	94%	96%	90%
Z.AI GLM 5.1	91%	99%	90%
Claude Opus 5	92%	98%	90%
GPT-5.6 Sol	92%	97%	89%
GPT-5.5 (Reasoning)	92%	97%	89%
GPT-5.6 Sol (Reasoning)	91%	98%	89%
GPT-5.5	91%	97%	88%
GPT-5.4	90%	97%	87%
Grok 4.5 (Reasoning, High)	90%	96%	87%
Grok 4.5 (Reasoning, Low)	91%	95%	87%
Claude Sonnet 5 (Reasoning, Low)	89%	97%	87%
GPT-5.6 Luna	88%	97%	87%
GPT-5.4 Mini (Reasoning)	90%	95%	87%
GPT-5.5 (Reasoning, Low)	91%	95%	87%
GPT-5.4 (Reasoning, Low)	90%	95%	86%
GPT-5.6 Terra	91%	96%	86%
Claude Opus 4.7 (Reasoning)	89%	97%	86%
MoonshotAI: Kimi K2.6	88%	97%	86%

	Score	Cost	Speed	Stability
Z.AI GLM 5.1	91%	$0.014	1.2m	90%
GPT-5.4 Mini (Reasoning)	90%	$0.017	22.1s	87%
Grok 4.5 (Reasoning, Low)	91%	$0.017	44.0s	87%
GPT-5.6 Luna	88%	$0.015	14.9s	87%
Muse Spark 1.1 (Reasoning, Medium)	90%	$0.015	19.4s	85%
Z.AI GLM 5 Turbo	88%	$0.0072	27.5s	86%
Muse Spark 1.1 (Reasoning, Minimal)	90%	$0.012	14.6s	83%
GPT-5.6 Terra	91%	$0.036	28.1s	86%
GPT-5.4 Mini (Reasoning, Low)	88%	$0.013	14.9s	84%
GPT-5.6 Luna (Reasoning)	88%	$0.016	14.9s	85%
GPT-5.6 Terra (Reasoning)	90%	$0.038	28.1s	85%
Claude Sonnet 5 (Reasoning, Low)	89%	$0.038	41.0s	87%
Grok 4.5 (Reasoning, High)	90%	$0.030	1.4m	87%
GPT-5.4	90%	$0.039	1.1m	87%
Aion 3.0 Mini	88%	$0.0062	1.1m	84%
DeepSeek V4 Pro	88%	$0.0053	55.2s	84%
Claude Opus 5 (Reasoning, Low)	94%	$0.103	54.5s	90%
MoonshotAI: Kimi K3 (Reasoning, Low)	90%	$0.024	56.3s	84%
GPT-5.4 (Reasoning)	93%	$0.075	2.1m	91%
Gemini 3.5 Flash Lite (Reasoning, Minimal)	85%	$0.0032	4.3s	82%

Rank	Model	Avg. Cost	Avg. Time	Stability	# 1	# 2	# 3	# 4	# 5	Total
17	Claude Opus 5 (Reasoning, Low)	$0.103	54.5s	90%	97	95	94	93	91	94%
24	Claude Opus 5 (Reasoning)	$0.111	1.0m	91%	96	95	94	93	91	93%
19	GPT-5.4 (Reasoning)	$0.075	2.1m	91%	94	93	93	92	92	93%
21	Claude Opus 5	$0.094	47.9s	90%	93	93	92	92	90	92%
23	GPT-5.6 Sol	$0.088	54.9s	89%	94	92	92	91	91	92%
58	GPT-5.5 (Reasoning)	$0.123	1.5m	89%	94	93	92	91	89	92%
1	Z.AI GLM 5.1	$0.014	1.2m	90%	92	92	91	91	91	91%
64	GPT-5.5	$0.116	1.5m	88%	94	92	91	90	89	91%
29	GPT-5.6 Sol (Reasoning)	$0.090	56.0s	89%	92	92	91	91	89	91%
3	Grok 4.5 (Reasoning, Low)	$0.017	44.0s	87%	94	92	91	90	87	91%
74	GPT-5.5 (Reasoning, Low)	$0.120	1.5m	87%	94	92	91	89	88	91%
8	GPT-5.6 Terra	$0.036	28.1s	86%	94	91	90	90	87	91%
11	GPT-5.6 Terra (Reasoning)	$0.038	28.1s	85%	94	93	91	90	85	90%
43	Claude Sonnet 4.6 (Reasoning)	$0.074	1.2m	85%	95	92	90	88	87	90%
5	Muse Spark 1.1 (Reasoning, Medium)	$0.015	19.4s	85%	95	92	91	87	86	90%
22	GPT-5.4 (Reasoning, Low)	$0.048	1.1m	86%	92	92	91	89	86	90%
14	GPT-5.4	$0.039	1.1m	87%	92	91	89	89	89	90%
2	GPT-5.4 Mini (Reasoning)	$0.017	22.1s	87%	92	92	91	88	86	90%
13	Grok 4.5 (Reasoning, High)	$0.030	1.4m	87%	92	91	91	89	86	90%
7	Muse Spark 1.1 (Reasoning, Minimal)	$0.012	14.6s	83%	96	92	92	87	82	90%
18	MoonshotAI: Kimi K3 (Reasoning, Low)	$0.024	56.3s	84%	94	91	88	88	87	90%
12	Claude Sonnet 5 (Reasoning, Low)	$0.038	41.0s	87%	91	91	89	89	87	89%
51	GPT-5.1	$0.046	2.1m	84%	94	92	89	88	85	89%
41	Claude Opus 4.7 (Reasoning)	$0.086	29.8s	86%	92	90	89	88	88	89%
90	GPT-5	$0.061	3.9m	85%	92	91	89	88	87	89%
27	Claude Sonnet 4.5	$0.040	37.3s	83%	92	92	89	89	83	89%
69	Claude Opus 4.8 (Reasoning, Low)	$0.082	39.3s	82%	94	90	87	87	86	89%
25	Aion 3.0	$0.031	1.0m	84%	91	90	90	89	83	89%
4	GPT-5.6 Luna	$0.015	14.9s	87%	90	89	89	88	86	88%
33	Claude Sonnet 4.6	$0.034	35.1s	82%	94	89	87	86	85	88%
34	Claude Sonnet 5	$0.033	32.8s	82%	92	92	88	85	84	88%
15	Aion 3.0 Mini	$0.0062	1.1m	84%	92	90	88	86	85	88%
9	GPT-5.4 Mini (Reasoning, Low)	$0.013	14.9s	84%	92	89	87	87	87	88%
38	Z.AI GLM 5	$0.0075	50.7s	79%	93	93	90	88	77	88%
6	Z.AI GLM 5 Turbo	$0.0072	27.5s	86%	90	90	90	86	85	88%
133	MoonshotAI: Kimi K2.6	$0.063	6.5m	86%	90	89	88	87	86	88%
71	Claude Opus 4.8 (Reasoning)	$0.083	39.0s	82%	93	90	89	86	81	88%
70	Claude Opus 4.6 (Reasoning)	$0.086	1.2m	86%	90	89	88	87	86	88%
10	GPT-5.6 Luna (Reasoning)	$0.016	14.9s	85%	90	88	87	87	86	88%
16	DeepSeek V4 Pro	$0.0053	55.2s	84%	91	90	89	85	84	88%
52	Claude Opus 4.5	$0.067	41.5s	84%	91	88	88	87	83	87%
31	DeepSeek V4 Pro (Reasoning)	$0.0092	2.0m	85%	89	89	88	86	85	87%
65	Claude Opus 4.7	$0.082	30.0s	83%	90	90	87	87	83	87%
97	Qwen3.6 Max Preview	$0.051	3.4m	82%	91	88	87	86	83	87%
28	Qwen 3.5 397B A17B	$0.012	1.3m	83%	89	89	86	86	85	87%
66	Claude Sonnet 4	$0.037	42.9s	78%	95	90	87	83	80	87%
37	MiniMax M2.7	$0.0029	1.0m	80%	92	89	86	84	83	87%
35	Qwen3 235B A22B Instruct 2507	$0.0015	48.5s	80%	93	88	86	85	82	87%
32	Z.AI GLM 5.2 (Reasoning, High)	$0.0093	50.3s	82%	90	89	87	86	82	87%
155	Claude Opus 4	$0.254	1.5m	83%	90	88	87	85	84	87%
46	Qwen 3.5 Plus (2026-04-20)	$0.020	2.0m	84%	88	88	87	85	84	86%
134	Gemini 3.1 Pro (Preview)	$0.146	2.4m	84%	88	87	87	86	84	86%
78	Qwen 3.6 27B	$0.023	2.4m	81%	91	88	87	87	80	86%
92	MiniMax M3	$0.0065	2.8m	76%	94	90	85	84	78	86%
116	Claude Opus 4.6	$0.082	1.1m	75%	96	88	87	82	77	86%
30	GPT-5.4 Mini	$0.014	15.8s	81%	90	89	87	85	80	86%
45	MoonshotAI: Kimi K3 (Reasoning, High)	$0.033	1.3m	85%	87	86	86	85	85	86%
48	Claude Sonnet 5 (Reasoning)	$0.038	40.3s	82%	89	88	86	85	83	86%
104	Thinking Machines Inkling (Reasoning)	$0.031	2.9m	78%	92	89	86	82	81	86%
26	DeepSeek V4 Flash (Reasoning)	$0.0006	28.2s	81%	90	89	87	84	80	86%
20	Gemini 3.5 Flash Lite (Reasoning, Minimal)	$0.0032	4.3s	82%	89	86	86	85	81	85%
40	Writer: Palmyra X5	$0.012	19.1s	80%	90	87	86	81	81	85%
86	Grok 4.20 (Reasoning)	$0.020	1.6m	77%	92	86	83	82	82	85%
44	Qwen 3.6 Flash	$0.012	48.3s	81%	88	88	86	84	81	85%
56	Gemini 2.5 Pro	$0.035	31.3s	81%	88	88	85	83	82	85%
54	Qwen 3.6 35B	$0.012	1.1m	80%	89	86	84	84	82	85%
39	GPT-5.4 Nano (Reasoning, Low)	$0.0045	19.4s	80%	89	88	87	81	78	85%
82	DeepSeek V4 Flash	$0.0008	2.1m	78%	90	87	84	82	80	85%
50	Gemini 3.5 Flash Lite (Reasoning)	$0.0031	4.1s	76%	90	89	86	85	74	85%
42	Claude Haiku 4.5	$0.014	22.8s	81%	87	86	84	83	82	84%
59	Grok 4.3	$0.0090	34.9s	78%	91	85	84	81	81	84%
62	Grok 4.3 (Reasoning)	$0.015	1.4m	81%	87	85	84	83	82	84%
79	Gemini 3.6 Flash (Reasoning)	$0.051	33.3s	80%	88	86	85	83	79	84%
107	Qwen3.7 Max	$0.072	2.1m	82%	86	85	85	85	81	84%
120	ByteDance Seed 2.0 Mini	$0.0045	4.9m	80%	88	84	83	83	82	84%
47	Grok 4.20	$0.011	41.9s	81%	86	85	85	83	80	84%
36	GPT-5.4 Nano	$0.0047	16.7s	82%	86	84	84	83	82	84%
114	MoonshotAI: Kimi K2.5	$0.012	4.3m	80%	86	86	86	82	79	84%
53	Mistral Large 3	$0.0037	29.1s	78%	88	85	85	83	77	83%
80	WizardLM 2 8x22b	$0.0038	2.1m	80%	87	84	84	81	81	83%
55	GPT-5.4 Nano (Reasoning)	$0.0047	21.6s	78%	88	83	82	82	80	83%
73	DeepSeek V3 (2025-03-24)	$0.0014	20.7s	74%	90	87	83	81	74	83%
49	Mistral Small 4 (Reasoning)	$0.0022	28.7s	79%	86	85	84	82	78	83%
63	Xiaomi MIMO v2.5 Pro	$0.0090	51.5s	80%	86	85	85	80	78	83%
85	Aion 2.0	$0.0073	1.1m	77%	86	86	83	83	75	83%
84	DeepSeek V3.2	$0.0019	1.4m	77%	87	85	82	81	79	83%
57	Qwen 3.5 Flash	$0.0024	49.3s	80%	86	84	84	80	80	83%
103	GPT-5.2	$0.044	1.2m	78%	87	86	84	78	78	83%
68	Qwen 3.5 9B	$0.0011	1.3m	80%	84	84	83	82	80	82%
109	Gemini 3.5 Flash (Reasoning)	$0.083	42.4s	79%	86	84	83	81	79	82%
75	Gemini 3.6 Flash (Reasoning, Minimal)	$0.018	12.2s	77%	86	85	83	82	75	82%
76	Mistral Large 2	$0.015	25.6s	77%	86	84	84	82	75	82%
83	Qwen 3.5 35B	$0.013	42.6s	77%	87	82	81	80	80	82%
61	Mistral Medium 3.1	$0.0049	39.2s	80%	84	84	83	81	79	82%
67	Qwen 3 32B	$0.0016	54.7s	79%	84	83	82	81	80	82%
77	Qwen 3.5 27B	$0.011	50.3s	79%	84	83	83	82	77	82%
81	o4 Mini	$0.014	24.6s	77%	84	84	82	78	78	81%
88	Thinking Machines Inkling	$0.0084	1.0m	78%	84	83	82	80	77	81%
89	Hermes 3 405B	$0.0050	26.4s	75%	86	86	86	80	69	81%
60	Ministral 3 3B	$0.0005	2.9s	78%	83	83	81	80	79	81%
93	Qwen 3.5 122B	$0.014	33.9s	75%	87	81	80	80	77	81%
72	Mistral Small 4	$0.0013	11.2s	77%	85	81	81	79	77	81%
96	o4 Mini High	$0.024	41.4s	77%	84	81	80	79	78	81%
100	GPT-4o, Aug. 6th (temp=1)	$0.021	30.9s	75%	84	84	79	78	77	81%
87	Qwen 3.5 Plus (2026-02-15)	$0.0076	36.0s	77%	83	83	81	80	76	80%
105	GPT-4.1	$0.018	49.1s	75%	85	82	80	78	75	80%
119	MiniMax M2.5	$0.0035	2.0m	73%	85	84	79	77	77	80%
121	Z.AI GLM 4.7	$0.0085	1.3m	71%	88	82	79	76	75	80%
95	Gemma 3 27B	$0.0009	41.6s	74%	84	83	79	76	76	80%
111	Z.AI GLM 4.5	$0.0039	23.4s	70%	88	85	81	78	67	80%
112	ByteDance Seed 2.0 Lite	$0.011	1.9m	76%	82	81	81	80	74	80%
94	Z.AI GLM 4.6	$0.0049	28.0s	75%	83	81	81	79	73	79%
91	Gemini 3.5 Flash (Reasoning, Minimal)	$0.013	8.6s	76%	83	80	79	78	76	79%
98	Laguna XS 2.1	$0.0004	10.0s	72%	86	82	82	73	71	79%
101	ByteDance Seed 1.6 Flash	$0.0013	26.4s	74%	83	80	78	76	76	79%
102	Z.AI GLM 4.5 Air	$0.0027	46.6s	75%	82	79	78	77	77	78%
118	DeepSeek V3 (2024-12-26)	$0.0026	37.2s	70%	87	79	79	73	73	78%
115	GPT-5 Mini	$0.0093	1.1m	74%	81	81	80	75	72	78%
99	GPT-4.1 Mini	$0.0030	18.5s	74%	81	79	78	78	74	78%
108	Gemma 3 12B	$0.0008	47.9s	73%	80	80	79	79	71	78%
110	Gemini 2.5 Flash (Reasoning)	$0.010	19.0s	73%	83	79	78	76	73	78%
138	Gemma 4 31B (Reasoning)	$0.0017	2.8m	74%	82	78	77	76	75	78%
123	Z.AI GLM 4.7 Flash	$0.0016	1.1m	71%	82	82	77	75	72	78%
124	Gemma 4 31B	$0.0013	1.7m	73%	81	78	77	76	73	77%
126	DeepSeek V3.1	$0.0022	1.7m	73%	80	80	78	77	71	77%
106	GPT-4o Mini (temp=1)	$0.0015	38.2s	75%	79	78	78	75	75	77%
125	Hermes 3 70B	$0.0016	1.5m	73%	81	80	80	73	70	77%
131	Cohere Command R+ (Aug. 2024)	$0.023	56.0s	73%	80	79	78	75	70	77%
113	Gemini 2.5 Flash	$0.0049	9.8s	72%	80	77	77	76	72	76%
137	DeepSeek-V2 Chat	$0.0025	45.9s	69%	83	80	75	73	71	76%
128	Ministral 8B	$0.0005	8.6s	68%	82	81	76	76	66	76%
144	ByteDance Seed 1.6	$0.0096	1.8m	69%	82	77	74	74	74	76%
130	Ministral 3 14B	$0.0011	8.3s	68%	82	80	74	73	71	76%
146	Gemma 4 26B (Reasoning)	$0.0015	1.6m	67%	84	78	74	72	70	76%
117	Ministral 3B	$0.0002	2.5s	71%	79	79	75	74	72	76%
140	Arcee AI: Trinity Mini	$0.0004	9.4s	65%	86	76	74	72	70	76%
122	Gemini 3 Flash (Preview)	$0.0070	20.2s	72%	78	76	74	74	74	75%
139	Ministral 3 8B	$0.0008	6.2s	66%	82	80	75	75	65	75%
127	Xiaomi MIMO v2.5	$0.0049	27.2s	71%	81	78	77	71	70	75%
136	Gemma 4 26B	$0.0011	59.7s	71%	80	77	76	73	70	75%
135	Gemini 3 Flash (Preview, Reasoning)	$0.011	25.7s	71%	78	77	77	75	67	75%
132	Laguna S 2.1	$0.0006	17.1s	69%	80	76	75	71	69	74%
145	Cydonia 24B V4.1	$0.0017	47.4s	66%	84	77	75	70	66	74%
129	Mistral NeMO	$0.0008	7.6s	70%	79	77	76	70	68	74%
142	Gemini 2.5 Flash Lite (Reasoning)	$0.0025	21.0s	68%	77	76	72	71	69	73%
143	GPT-4.1 Nano	$0.0008	14.9s	67%	79	73	73	69	67	72%
147	GPT-4o Mini (temp=0)	$0.0013	40.4s	67%	76	74	71	71	68	72%
150	Llama 3.1 70B	$0.0026	48.5s	65%	81	75	75	65	63	72%
141	Gemini 2.5 Flash Lite	$0.0010	7.2s	69%	73	73	71	70	70	72%
148	Gemma 3 4B	$0.0003	21.7s	65%	79	72	71	69	66	71%
156	GPT-4o, Aug. 6th (temp=0)	$0.050	40.8s	66%	78	74	74	68	63	71%
151	Qwen 2.5 72B	$0.0013	35.7s	66%	74	73	72	67	63	70%
149	Gemini 3.1 Flash Lite (Reasoning)	$0.0036	9.7s	66%	72	71	69	69	66	69%
152	Gemini 3.1 Flash Lite (Preview)	$0.0036	8.3s	65%	75	72	72	64	64	69%
153	Nemotron 3 Super	$0.0000	51.4s	65%	75	69	69	67	66	69%
154	Gemini 3.1 Flash Lite	$0.0036	21.4s	65%	69	69	67	66	64	67%
161	Mistral Small 3.2 24B	$0.012	10.0m	63%	70	69	67	67	61	67%
157	GPT-OSS 120B	$0.0014	50.5s	62%	71	68	66	65	63	67%
158	GPT-5 Nano	$0.0043	1.5m	62%	72	67	66	65	62	66%
159	Inception Mercury 2	$0.0026	5.5s	59%	69	65	62	61	61	64%
160	Nemotron 3 Nano	$0.0010	38.8s	55%	67	65	61	58	56	61%
82.25%

Median	Evaluator	Top 3	Flop 3
82.7%	"Not X but Y" pattern overuse	100Qwen 3.5 9B 100Mistral NeMO 100Claude Opus 5	0GPT-5 Nano 0Gemini 2.5 Flash Lite 16Gemini 2.5 Flash Lite (Reasoning)
80.7%	Adverb-first sentence starts	100Claude Haiku 4.5 100Qwen3 235B A22B Instruct 2507 100Claude Sonnet 5	7Nemotron 3 Nano 10ByteDance Seed 2.0 Lite 16Mistral Small 3.2 24B
100.0%	Adverbs in dialogue tags	100Gemini 3.6 Flash (Reasoning, Minimal) 100Claude Sonnet 4.5 100o4 Mini	33GPT-4o Mini (temp=1) 47Cydonia 24B V4.1 53Claude Sonnet 4
91.8%	AI-ism adverb frequency	100GPT-5.6 Sol (Reasoning) 100o4 Mini High 100GPT-5.6 Terra (Reasoning)	71Cydonia 24B V4.1 72GPT-4.1 Nano 75Z.AI GLM 4.5
100.0%	AI-ism character names	100Mistral Small 4 100Qwen 2.5 72B 100Gemini 2.5 Flash	88DeepSeek V4 Pro 92Claude Opus 4 96ByteDance Seed 1.6 Flash
100.0%	AI-ism location names	100Claude Haiku 4.5 100DeepSeek V4 Pro 100Claude Opus 4.7 (Reasoning)	—
33.7%	AI-ism word frequency	76ByteDance Seed 2.0 Mini 76Claude Opus 5 (Reasoning) 75Claude Opus 5	0GPT-4.1 Nano 0o4 Mini 0Ministral 8B
100.0%	Cliché density	100o4 Mini High 100Mistral Large 3 100Z.AI GLM 4.5 Air	47Mistral Small 3.2 24B 60Qwen 2.5 72B 67GPT-4.1 Nano
55.3%	Dialogue tag variety (said vs. fancy)	100Mistral Large 2 100Aion 3.0 Mini 100GPT-5.6 Sol (Reasoning)	0o4 Mini High 0Gemma 3 12B 0Gemini 3.5 Flash (Reasoning)
97.9%	Em-dash & semicolon overuse	100Z.AI GLM 5.2 (Reasoning, High) 100GPT-5.1 100Qwen 3.6 Flash	0Ministral 3 8B 0GPT-4o Mini (temp=1) 0GPT-4.1 Nano
100.0%	Emotion telling (show vs. tell)	100Grok 4.3 100GPT-5.4 Nano (Reasoning, Low) 100Mistral Medium 3.1	77Mistral Small 3.2 24B 89Mistral NeMO 90Llama 3.1 70B
98.9%	Filter word density	100GPT-5.2 100DeepSeek V4 Pro (Reasoning) 100Claude Opus 4.7 (Reasoning)	11Gemini 2.5 Flash Lite (Reasoning) 15Inception Mercury 2 17Nemotron 3 Nano
100.0%	Gibberish response detection	100GPT-5.4 Mini (Reasoning, Low) 100Gemma 4 26B (Reasoning) 100Gemini 2.5 Flash (Reasoning)	80Llama 3.1 70B 88DeepSeek V3 (2025-03-24) 92Cydonia 24B V4.1
100.0%	Markdown formatting overuse	100Thinking Machines Inkling (Reasoning) 100GPT-5.4 Mini (Reasoning, Low) 100Qwen 3.5 9B	51ByteDance Seed 1.6 Flash 67Mistral Medium 3.1 80Aion 2.0
100.0%	Missing dialogue indicators (quotation marks)	100Gemini 3.5 Flash Lite (Reasoning) 100ByteDance Seed 2.0 Mini 100o4 Mini High	80Qwen 3.5 35B 80Muse Spark 1.1 (Reasoning, Minimal) 80GPT-5
93.3%	Name drop frequency	100DeepSeek V3.1 100GPT-5.1 100Gemini 3.1 Flash Lite (Reasoning)	24GPT-5.6 Luna 28GPT-5.6 Luna (Reasoning) 47GPT-5.6 Sol (Reasoning)
80.0%	Narrator intent-glossing	100MoonshotAI: Kimi K3 (Reasoning, High) 100Muse Spark 1.1 (Reasoning, Medium) 100Qwen 3.6 27B	0Nemotron 3 Nano 3Inception Mercury 2 5GPT-5 Nano
100.0%	Overuse of "that" (subordinate clause padding)	100GPT-5.1 100Qwen3.6 Max Preview 100GPT-4.1 Nano	40ByteDance Seed 2.0 Lite 77Hermes 3 70B 80Mistral Small 3.2 24B
100.0%	Paragraph length variance	100GPT-5.4 Nano (Reasoning) 100MiniMax M2.5 100DeepSeek V4 Flash	5Grok 4.3 (Reasoning) 32Nemotron 3 Nano 43GPT-4o, Aug. 6th (temp=0)
99.4%	Passive voice overuse	100Claude Sonnet 4 100o4 Mini 100GPT-5.6 Luna	86Laguna XS 2.1 90ByteDance Seed 2.0 Mini 91ByteDance Seed 2.0 Lite
97.6%	Past progressive (was/were + -ing) overuse	100GPT-5.6 Luna (Reasoning) 100GPT-5.6 Sol (Reasoning) 100Thinking Machines Inkling (Reasoning)	33Z.AI GLM 4.7 Flash 34Ministral 3 8B 36Gemini 3.1 Flash Lite (Reasoning)
92.9%	Pronoun-first sentence starts	100Qwen3 235B A22B Instruct 2507 100Claude Haiku 4.5 100Claude Opus 4.8 (Reasoning, Low)	14Gemini 3.1 Flash Lite (Reasoning) 16Gemini 3.1 Flash Lite 16Gemini 3.1 Flash Lite (Preview)
96.3%	Purple prose (modifier overload)	100Nemotron 3 Nano 100Qwen 3.5 9B 100GPT-5 Mini	68Cydonia 24B V4.1 79Gemini 3 Flash (Preview, Reasoning) 81Gemini 2.5 Flash (Reasoning)
100.0%	Repeated phrase echo	100Claude Opus 4.6 (Reasoning) 100Claude Opus 4.8 (Reasoning) 100Cohere Command R+ (Aug. 2024)	—
100.0%	Sentence length variance	100Qwen 3.5 122B 100GPT-5.6 Terra (Reasoning) 100Writer: Palmyra X5	66Nemotron 3 Nano 79GPT-4o, Aug. 6th (temp=0) 90Inception Mercury 2
49.0%	Sentence opener variety	89Gemini 3.5 Flash Lite (Reasoning, Minimal) 87Gemini 3.5 Flash Lite (Reasoning) 87DeepSeek V3 (2025-03-24)	25GPT-5 Nano 30Qwen 3.5 35B 31Gemma 4 26B
53.9%	Subject-first sentence starts	100Qwen3 235B A22B Instruct 2507 100Writer: Palmyra X5 100Claude Opus 5 (Reasoning)	0Qwen 3.5 9B 0GPT-OSS 120B 0Inception Mercury 2
35.5%	Subordinate conjunction sentence starts	88Gemini 2.5 Flash Lite 80Claude Opus 4.7 (Reasoning) 77Cydonia 24B V4.1	0Qwen 3.5 122B 0DeepSeek V3 (2025-03-24) 0Gemini 3.5 Flash Lite (Reasoning)
71.2%	Technical jargon density	100GPT-5.6 Sol 100Qwen 3.5 Flash 100Qwen 3.5 9B	0GPT-5 Nano 0Nemotron 3 Nano 2Gemini 2.5 Flash Lite (Reasoning)
80.0%	Useless dialogue additions	100Qwen 3.5 397B A17B 100Qwen 3.5 9B 100GPT-5.5	0Gemma 3 12B 0GPT-4o Mini (temp=0) 0Qwen 2.5 72B

Bad Writing Habits

Horror: alone in an eerie place at night

Performance Score Distribution (Top 20)

Price-Performance Score Distribution (Top 20)

Most Stable Models (Top 20)

Top Overall Models (Top 20)