Thriller: chase through city streets

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)	94%
GPT-5.4	93%
Claude Opus 5 (Reasoning, Low)	93%
MoonshotAI: Kimi K3 (Reasoning, High)	93%
Grok 4.5 (Reasoning, High)	92%
MoonshotAI: Kimi K3 (Reasoning, Low)	92%
GPT-5.4 (Reasoning, Low)	91%
Qwen3 235B A22B Instruct 2507	91%
Muse Spark 1.1 (Reasoning, Medium)	91%
Qwen 3.5 397B A17B	91%
Claude Opus 5	91%
Z.AI GLM 5	91%
GPT-5.4 (Reasoning)	91%
Z.AI GLM 5 Turbo	90%
Claude Opus 4.8 (Reasoning, Low)	90%
Claude Sonnet 4.6 (Reasoning)	90%
Claude Opus 4.6 (Reasoning)	90%
GPT-5.5 (Reasoning)	90%
Muse Spark 1.1 (Reasoning, Minimal)	90%
GPT-5.6 Sol (Reasoning)	90%

	Score	Cost	Time
Z.AI GLM 5 Turbo	90%	$0.0078	26.6s
DeepSeek V4 Pro	86%	$0.0050	50.1s
Muse Spark 1.1 (Reasoning, Minimal)	90%	$0.014	18.7s
Writer: Palmyra X5	90%	$0.011	18.7s
Qwen3 235B A22B Instruct 2507	91%	$0.0014	59.9s
DeepSeek V4 Flash	88%	$0.0007	26.2s
DeepSeek V4 Flash (Reasoning)	89%	$0.0005	21.4s
Muse Spark 1.1 (Reasoning, Medium)	91%	$0.016	24.8s
Xiaomi MIMO v2.5 Pro	89%	$0.0081	44.9s
MoonshotAI: Kimi K3 (Reasoning, Low)	92%	$0.026	1.0m
Z.AI GLM 5	91%	$0.0075	44.3s
GPT-5.6 Luna (Reasoning)	89%	$0.016	16.9s
MoonshotAI: Kimi K3 (Reasoning, High)	93%	$0.038	1.6m
GPT-5.4 Mini (Reasoning)	90%	$0.023	28.1s
GPT-5.6 Luna	89%	$0.014	14.4s
GPT-5.4 Mini (Reasoning, Low)	89%	$0.014	16.8s
Z.AI GLM 5.2 (Reasoning, High)	89%	$0.011	57.5s
GPT-5.4 Mini	88%	$0.015	16.7s
Grok 4.5 (Reasoning, High)	92%	$0.031	1.4m
Qwen 3.6 Flash	87%	$0.012	47.6s

	Score	Consistency	Stability
GPT-5.4	93%	99%	91%
Claude Opus 5 (Reasoning)	94%	96%	90%
Qwen3 235B A22B Instruct 2507	91%	98%	90%
MoonshotAI: Kimi K3 (Reasoning, Low)	92%	97%	90%
GPT-5.5 (Reasoning)	90%	99%	90%
GPT-5.4 (Reasoning, Low)	91%	97%	89%
Claude Opus 5 (Reasoning, Low)	93%	94%	89%
GPT-5.4 (Reasoning)	91%	98%	89%
GPT-5.6 Terra (Reasoning)	90%	97%	88%
Grok 4.5 (Reasoning, High)	92%	96%	88%
Claude Opus 4.8 (Reasoning, Low)	90%	97%	88%
GPT-5.6 Luna (Reasoning)	89%	98%	88%
GPT-5.5	90%	96%	87%
Qwen 3.5 397B A17B	91%	96%	87%
Writer: Palmyra X5	90%	96%	87%
Z.AI GLM 5.1	89%	98%	87%
GPT-5.4 Mini	88%	99%	87%
GPT-5.4 Mini (Reasoning)	90%	97%	87%
GPT-5.5 (Reasoning, Low)	90%	97%	87%
Xiaomi MIMO v2.5 Pro	89%	96%	87%

	Score	Cost	Speed	Stability
Qwen3 235B A22B Instruct 2507	91%	$0.0014	59.9s	90%
MoonshotAI: Kimi K3 (Reasoning, Low)	92%	$0.026	1.0m	90%
GPT-5.4	93%	$0.046	1.4m	91%
Writer: Palmyra X5	90%	$0.011	18.7s	87%
Z.AI GLM 5 Turbo	90%	$0.0078	26.6s	86%
Muse Spark 1.1 (Reasoning, Medium)	91%	$0.016	24.8s	86%
GPT-5.6 Luna (Reasoning)	89%	$0.016	16.9s	88%
Z.AI GLM 5	91%	$0.0075	44.3s	86%
Grok 4.5 (Reasoning, High)	92%	$0.031	1.4m	88%
GPT-5.4 Mini (Reasoning)	90%	$0.023	28.1s	87%
GPT-5.6 Terra (Reasoning)	90%	$0.040	33.9s	88%
Muse Spark 1.1 (Reasoning, Minimal)	90%	$0.014	18.7s	85%
GPT-5.4 (Reasoning, Low)	91%	$0.050	1.2m	89%
DeepSeek V4 Flash (Reasoning)	89%	$0.0005	21.4s	84%
Xiaomi MIMO v2.5 Pro	89%	$0.0081	44.9s	87%
GPT-5.4 Mini	88%	$0.015	16.7s	87%
GPT-5.4 Mini (Reasoning, Low)	89%	$0.014	16.8s	86%
GPT-5.6 Luna	89%	$0.014	14.4s	86%
Z.AI GLM 5.2 (Reasoning, High)	89%	$0.011	57.5s	86%
GPT-5.6 Terra	90%	$0.037	31.6s	86%

Rank	Model	Avg. Cost	Avg. Time	Stability	# 1	# 2	# 3	# 4	# 5	Total
21	Claude Opus 5 (Reasoning)	$0.112	1.0m	90%	97	95	94	92	91	94%
3	GPT-5.4	$0.046	1.4m	91%	94	93	93	92	92	93%
29	Claude Opus 5 (Reasoning, Low)	$0.106	1.1m	89%	96	95	95	90	89	93%
22	MoonshotAI: Kimi K3 (Reasoning, High)	$0.038	1.6m	85%	98	95	92	91	87	93%
9	Grok 4.5 (Reasoning, High)	$0.031	1.4m	88%	94	94	92	91	89	92%
2	MoonshotAI: Kimi K3 (Reasoning, Low)	$0.026	1.0m	90%	93	92	92	92	89	92%
13	GPT-5.4 (Reasoning, Low)	$0.050	1.2m	89%	93	93	92	90	89	91%
1	Qwen3 235B A22B Instruct 2507	$0.0014	59.9s	90%	92	92	91	91	90	91%
6	Muse Spark 1.1 (Reasoning, Medium)	$0.016	24.8s	86%	95	92	91	90	87	91%
26	Qwen 3.5 397B A17B	$0.0049	3.3m	87%	93	93	91	90	87	91%
54	Claude Opus 5	$0.102	55.0s	84%	97	93	90	88	88	91%
8	Z.AI GLM 5	$0.0075	44.3s	86%	94	92	90	89	88	91%
65	GPT-5.4 (Reasoning)	$0.109	3.0m	89%	92	91	90	90	89	91%
5	Z.AI GLM 5 Turbo	$0.0078	26.6s	86%	94	93	92	88	85	90%
31	Claude Opus 4.8 (Reasoning, Low)	$0.085	40.3s	88%	93	91	91	89	88	90%
32	Claude Sonnet 4.6 (Reasoning)	$0.065	1.1m	86%	93	92	91	90	86	90%
49	Claude Opus 4.6 (Reasoning)	$0.091	1.2m	85%	93	93	89	88	88	90%
62	GPT-5.5 (Reasoning)	$0.141	1.8m	90%	91	91	90	90	89	90%
12	Muse Spark 1.1 (Reasoning, Minimal)	$0.014	18.7s	85%	95	93	92	86	86	90%
45	GPT-5.6 Sol (Reasoning)	$0.093	1.1m	86%	93	93	89	88	88	90%
11	GPT-5.6 Terra (Reasoning)	$0.040	33.9s	88%	92	91	91	89	88	90%
4	Writer: Palmyra X5	$0.011	18.7s	87%	93	91	91	89	87	90%
10	GPT-5.4 Mini (Reasoning)	$0.023	28.1s	87%	93	91	90	89	88	90%
60	GPT-5.5 (Reasoning, Low)	$0.118	1.6m	87%	92	92	89	89	88	90%
61	GPT-5.5	$0.121	1.7m	87%	92	91	91	90	86	90%
33	Claude Sonnet 4.6	$0.036	40.3s	82%	95	94	89	87	84	90%
27	Claude Sonnet 4.5	$0.041	37.3s	85%	94	90	89	89	87	90%
20	GPT-5.6 Terra	$0.037	31.6s	86%	92	92	90	89	87	90%
41	GPT-5.1	$0.052	2.2m	86%	92	91	89	89	86	90%
14	DeepSeek V4 Flash (Reasoning)	$0.0005	21.4s	84%	93	92	89	88	85	89%
25	Z.AI GLM 5.1	$0.020	1.8m	87%	91	90	89	89	88	89%
58	Claude Opus 4.7	$0.085	31.4s	82%	94	93	90	89	81	89%
55	Claude Opus 4.6	$0.087	1.2m	84%	94	90	89	88	86	89%
7	GPT-5.6 Luna (Reasoning)	$0.016	16.9s	88%	90	90	89	88	88	89%
17	GPT-5.4 Mini (Reasoning, Low)	$0.014	16.8s	86%	91	90	89	88	86	89%
35	Claude Sonnet 5	$0.033	33.7s	82%	94	92	89	88	82	89%
15	Xiaomi MIMO v2.5 Pro	$0.0081	44.9s	87%	91	91	90	87	87	89%
85	DeepSeek V4 Pro (Reasoning)	$0.026	5.5m	85%	92	91	90	87	84	89%
19	Z.AI GLM 5.2 (Reasoning, High)	$0.011	57.5s	86%	91	90	89	89	85	89%
24	Grok 4.5 (Reasoning, Low)	$0.016	42.9s	85%	92	90	88	88	86	89%
52	GPT-5.6 Sol	$0.085	55.9s	85%	92	88	88	88	88	89%
69	Qwen3.6 Max Preview	$0.048	3.1m	84%	92	91	88	87	86	89%
18	GPT-5.6 Luna	$0.014	14.4s	86%	91	90	88	88	87	89%
28	Aion 3.0	$0.032	1.1m	86%	90	89	88	87	87	88%
16	GPT-5.4 Mini	$0.015	16.7s	87%	90	88	88	88	88	88%
30	MiniMax M3	$0.0049	2.2m	86%	90	89	88	88	86	88%
119	MoonshotAI: Kimi K2.6	$0.066	6.3m	85%	91	88	88	87	86	88%
23	DeepSeek V4 Flash	$0.0007	26.2s	84%	91	90	89	86	83	88%
59	Claude Opus 4.8 (Reasoning)	$0.086	41.8s	84%	90	89	88	87	84	88%
36	Aion 3.0 Mini	$0.0070	1.4m	83%	91	89	88	88	82	88%
48	Qwen 3.5 Plus (2026-04-20)	$0.017	1.6m	82%	92	91	90	82	81	87%
38	Qwen 3.6 Flash	$0.012	47.6s	81%	92	89	88	87	80	87%
50	Claude Opus 4.5	$0.069	43.9s	85%	89	88	88	86	84	87%
44	MiniMax M2.7	$0.0035	1.1m	80%	92	90	87	84	82	87%
43	Thinking Machines Inkling (Reasoning)	$0.027	47.7s	82%	91	87	86	85	85	87%
57	Claude Sonnet 5 (Reasoning)	$0.040	42.1s	81%	91	90	88	85	80	87%
92	MoonshotAI: Kimi K2.5	$0.026	3.4m	79%	91	90	86	85	81	87%
156	Claude Opus 4	$0.292	1.9m	80%	91	89	88	85	78	86%
64	Claude Sonnet 5 (Reasoning, Low)	$0.039	39.4s	80%	93	87	87	85	80	86%
82	Claude Opus 4.7 (Reasoning)	$0.091	33.5s	82%	89	88	85	85	85	86%
39	Grok 4.20 (Reasoning)	$0.016	1.1m	83%	89	89	88	83	82	86%
67	Claude Sonnet 4	$0.038	44.7s	80%	91	90	89	84	77	86%
42	MiniMax M2.5	$0.0034	1.6m	83%	89	88	87	86	82	86%
104	GPT-5	$0.068	4.0m	83%	89	86	86	85	85	86%
46	Qwen 3.6 35B	$0.012	1.0m	81%	89	89	86	84	82	86%
47	Grok 4.20	$0.011	38.2s	80%	91	87	86	84	81	86%
80	DeepSeek V4 Pro	$0.0050	50.1s	75%	93	93	92	82	69	86%
34	Gemini 3.5 Flash Lite (Reasoning)	$0.0037	5.5s	82%	89	86	86	85	82	86%
40	Mistral Medium 3.1	$0.0059	40.6s	82%	88	87	85	84	84	86%
56	Grok 4.3	$0.0090	24.3s	78%	91	87	84	83	81	85%
114	Qwen3.7 Max	$0.085	2.5m	82%	87	84	84	83	83	84%
74	Hermes 3 405B	$0.0054	37.5s	77%	90	89	85	80	78	84%
37	Gemini 3.5 Flash Lite (Reasoning, Minimal)	$0.0034	4.8s	82%	86	85	85	85	80	84%
51	GPT-5.4 Nano	$0.0048	16.7s	80%	87	87	84	82	81	84%
68	Gemini 3.6 Flash (Reasoning)	$0.048	30.1s	82%	85	85	84	84	83	84%
53	DeepSeek V3 (2025-03-24)	$0.0016	14.5s	80%	88	86	85	82	79	84%
132	Gemini 3.1 Pro (Preview)	$0.136	2.2m	81%	86	84	84	84	81	84%
86	Aion 2.0	$0.0076	1.4m	78%	88	85	84	82	78	84%
72	Z.AI GLM 4.5	$0.0039	28.5s	78%	88	86	84	84	76	84%
66	ByteDance Seed 1.6 Flash	$0.0012	24.5s	78%	87	85	85	85	76	84%
70	Z.AI GLM 4.7 Flash	$0.0017	1.2m	80%	87	84	83	83	80	84%
105	WizardLM 2 8x22b	$0.0040	2.8m	76%	90	83	82	82	79	83%
81	o4 Mini High	$0.021	44.5s	79%	87	86	84	80	78	83%
87	Claude Haiku 4.5	$0.014	22.0s	76%	87	87	83	82	76	83%
83	Qwen 3 32B	$0.0017	32.0s	76%	89	83	82	81	80	83%
71	Mistral Small 4	$0.0017	21.1s	78%	87	85	84	80	77	83%
88	Gemini 3.5 Flash (Reasoning, Minimal)	$0.018	11.8s	76%	89	83	82	81	78	83%
75	DeepSeek V3.2	$0.0020	1.3m	80%	84	84	82	82	80	83%
90	Grok 4.3 (Reasoning)	$0.016	1.3m	78%	87	86	85	78	77	83%
63	Qwen 3.5 Flash	$0.0022	51.7s	81%	85	83	83	82	81	83%
76	Qwen 3.5 122B	$0.017	37.1s	80%	84	84	82	82	81	83%
73	GPT-5.4 Nano (Reasoning)	$0.0056	21.4s	79%	87	83	83	80	79	82%
112	GPT-5.2	$0.059	1.8m	79%	85	84	83	81	79	82%
84	GPT-5 Mini	$0.010	1.0m	79%	85	83	82	82	80	82%
77	Mistral Small 4 (Reasoning)	$0.0028	30.6s	78%	86	84	83	82	77	82%
117	Qwen 3.5 9B	$0.0016	1.7m	73%	91	82	81	79	76	82%
109	Thinking Machines Inkling	$0.0061	1.1m	73%	88	86	82	80	73	82%
79	Hermes 3 70B	$0.0015	21.9s	78%	85	85	84	78	76	82%
106	Gemini 2.5 Pro	$0.036	36.4s	75%	87	85	83	79	74	82%
108	Gemini 3.5 Flash (Reasoning)	$0.073	38.1s	79%	84	82	82	81	79	82%
98	o4 Mini	$0.017	29.4s	75%	86	85	81	79	77	82%
89	GPT-5.4 Nano (Reasoning, Low)	$0.0049	18.3s	76%	85	84	80	80	79	81%
93	Gemma 3 27B	$0.0008	51.3s	76%	86	85	83	79	74	81%
91	Cydonia 24B V4.1	$0.0018	37.9s	76%	86	84	81	79	77	81%
97	Xiaomi MIMO v2.5	$0.0052	29.9s	75%	85	85	79	79	78	81%
101	Z.AI GLM 4.7	$0.011	1.3m	77%	85	83	82	78	78	81%
129	Z.AI GLM 4.6	$0.0066	1.0m	69%	89	86	77	77	75	81%
111	Gemma 4 26B (Reasoning)	$0.0014	1.5m	74%	87	84	83	78	72	81%
78	Gemini 2.5 Flash	$0.0057	10.8s	79%	82	81	81	81	79	81%
96	Gemini 2.5 Flash (Reasoning)	$0.0099	17.3s	75%	85	83	80	78	78	81%
107	Z.AI GLM 4.5 Air	$0.0028	41.6s	73%	86	85	80	78	75	81%
95	Gemini 2.5 Flash Lite	$0.0009	8.1s	74%	86	84	81	81	73	81%
116	DeepSeek V3.1	$0.0028	2.4m	76%	84	81	80	79	78	81%
110	GPT-4.1	$0.019	55.8s	75%	85	83	80	79	77	81%
99	Cohere Command R+ (Aug. 2024)	$0.025	31.5s	77%	84	81	81	80	77	80%
94	Mistral Large 3	$0.0043	29.5s	76%	84	84	82	79	74	80%
100	Mistral Large 2	$0.017	30.1s	77%	83	81	80	80	76	80%
139	Qwen 3.5 27B	$0.044	2.9m	77%	84	81	81	78	76	80%
155	Qwen 3.6 27B	$0.036	3.4m	65%	91	83	82	82	60	80%
118	Gemini 3.6 Flash (Reasoning, Minimal)	$0.019	13.2s	73%	86	80	78	78	77	80%
102	Qwen 3.5 35B	$0.0095	32.9s	76%	82	82	80	78	75	80%
122	ByteDance Seed 2.0 Lite	$0.012	2.1m	76%	83	80	79	78	77	79%
115	Qwen 3.5 Plus (2026-02-15)	$0.0068	28.0s	74%	84	79	78	77	76	79%
128	GPT-4o Mini (temp=1)	$0.0013	41.8s	70%	87	80	77	76	74	79%
124	DeepSeek V3 (2024-12-26)	$0.0027	1.2m	73%	83	82	77	76	76	79%
146	DeepSeek-V2 Chat	$0.0026	58.1s	66%	86	85	77	76	67	78%
113	GPT-4.1 Nano	$0.0008	14.4s	73%	82	81	78	77	73	78%
134	ByteDance Seed 1.6	$0.0098	1.7m	73%	83	78	77	77	74	78%
144	Laguna S 2.1	$0.0006	37.5s	66%	85	84	75	74	72	78%
120	Arcee AI: Trinity Mini	$0.0004	7.3s	72%	83	80	78	77	72	78%
121	GPT-4.1 Mini	$0.0027	17.2s	72%	83	78	77	77	72	78%
103	Laguna XS 2.1	$0.0004	11.2s	76%	79	79	78	77	76	78%
130	Ministral 3 8B	$0.0028	1.5m	73%	82	80	79	74	72	77%
127	Ministral 3 14B	$0.0012	11.9s	70%	83	82	77	73	72	77%
138	Gemma 4 31B (Reasoning)	$0.0018	2.3m	74%	79	79	78	78	72	77%
152	ByteDance Seed 2.0 Mini	$0.0041	4.2m	71%	83	77	76	75	74	77%
131	GPT-4o, Aug. 6th (temp=1)	$0.020	16.4s	72%	82	77	76	75	74	77%
123	Ministral 3B	$0.0002	5.0s	72%	82	80	78	74	70	77%
125	GPT-4o Mini (temp=0)	$0.0014	54.5s	74%	79	78	76	76	74	77%
143	Qwen 2.5 72B	$0.0014	42.7s	70%	82	79	75	73	72	76%
126	Ministral 8B	$0.0006	8.3s	72%	81	77	76	75	72	76%
136	Gemma 3 4B	$0.0003	21.4s	70%	81	80	77	71	70	76%
145	Gemini 3 Flash (Preview, Reasoning)	$0.011	26.8s	69%	83	78	76	73	69	76%
137	Gemini 2.5 Flash Lite (Reasoning)	$0.0030	31.4s	71%	79	78	76	74	70	76%
149	Gemma 4 31B	$0.0015	1.8m	68%	83	75	74	73	72	75%
141	Gemma 4 26B	$0.0012	35.8s	71%	80	75	75	73	73	75%
135	Ministral 3 3B	$0.0005	3.0s	70%	79	77	76	75	67	75%
142	Gemma 3 12B	$0.0004	35.6s	71%	80	78	77	70	70	75%
151	Mistral NeMO	$0.0009	9.5s	64%	87	74	73	70	70	75%
140	GPT-4o, Aug. 6th (temp=0)	$0.022	15.4s	73%	77	77	76	73	72	75%
133	Llama 3.1 70B	$0.0020	22.2s	72%	77	76	75	75	72	75%
148	Gemini 3 Flash (Preview)	$0.0075	17.5s	69%	79	75	73	71	71	74%
147	Gemini 3.1 Flash Lite (Reasoning)	$0.0035	9.4s	69%	77	76	73	71	71	74%
154	Gemini 3.1 Flash Lite	$0.0034	13.9s	63%	80	75	69	69	68	72%
153	Gemini 3.1 Flash Lite (Preview)	$0.0039	9.2s	66%	77	71	71	70	67	71%
150	Nemotron 3 Super	$0.0000	46.2s	70%	72	72	72	69	69	71%
157	GPT-5 Nano	$0.0045	1.7m	68%	70	70	70	68	67	69%
158	GPT-OSS 120B	$0.0018	1.2m	64%	74	68	68	67	65	68%
160	Nemotron 3 Nano	$0.0010	42.3s	61%	74	68	66	64	62	67%
161	Mistral Small 3.2 24B	$0.012	11.5m	62%	72	68	67	67	60	67%
159	Inception Mercury 2	$0.0032	6.6s	61%	72	68	66	64	63	66%
83.30%

Median	Evaluator	Top 3	Flop 3
100.0%	"Not X but Y" pattern overuse	100Z.AI GLM 5.1 100Qwen 3.6 Flash 100Qwen 3.5 Plus (2026-04-20)	43GPT-5 Nano 44Gemini 2.5 Flash Lite (Reasoning) 49Gemini 2.5 Flash
59.7%	Adverb-first sentence starts	100Writer: Palmyra X5 100Qwen3 235B A22B Instruct 2507 100Laguna S 2.1	0Gemini 3.5 Flash Lite (Reasoning, Minimal) 0Inception Mercury 2 0GPT-OSS 120B
100.0%	Adverbs in dialogue tags	100GPT-5.5 100GPT-5 100Muse Spark 1.1 (Reasoning, Medium)	44GPT-4o, Aug. 6th (temp=1) 56Laguna XS 2.1 58Laguna S 2.1
95.0%	AI-ism adverb frequency	100GPT-5.4 (Reasoning) 100GPT-5.6 Sol (Reasoning) 100GPT-5.4	74Laguna S 2.1 75Qwen 3.6 27B 79GPT-4.1 Nano
100.0%	AI-ism character names	100Gemini 2.5 Flash Lite 100ByteDance Seed 2.0 Lite 100Z.AI GLM 4.5	88Gemma 3 4B 92MiniMax M2.7 92Laguna XS 2.1
100.0%	AI-ism location names	100WizardLM 2 8x22b 100Claude Opus 4.7 (Reasoning) 100Ministral 3 3B	—
53.8%	AI-ism word frequency	89Claude Opus 5 (Reasoning, Low) 88Claude Opus 5 88Claude Opus 5 (Reasoning)	0GPT-4o, Aug. 6th (temp=1) 0GPT-4o, Aug. 6th (temp=0) 0GPT-4.1 Nano
100.0%	Cliché density	100Z.AI GLM 4.7 100Thinking Machines Inkling (Reasoning) 100DeepSeek V4 Pro (Reasoning)	27Mistral NeMO 33Qwen 2.5 72B 47Inception Mercury 2
76.2%	Dialogue tag variety (said vs. fancy)	100Muse Spark 1.1 (Reasoning, Medium) 100GPT-5.4 Mini (Reasoning) 100Grok 4.5 (Reasoning, Low)	0Inception Mercury 2 0GPT-4o, Aug. 6th (temp=1) 0GPT-OSS 120B
99.2%	Em-dash & semicolon overuse	100Claude Sonnet 4.5 100Grok 4.3 (Reasoning) 100GPT-5.4 Mini (Reasoning)	0GPT-4o Mini (temp=1) 0Mistral Large 2 0Mistral Small 4
100.0%	Emotion telling (show vs. tell)	100GPT-4o Mini (temp=1) 100Grok 4.5 (Reasoning, Low) 100Gemini 3.6 Flash (Reasoning, Minimal)	85Mistral Small 3.2 24B 97Llama 3.1 70B 97Nemotron 3 Nano
98.4%	Filter word density	100Xiaomi MIMO v2.5 Pro 100GPT-5.4 Nano 100Mistral Small 4	35Nemotron 3 Nano 37Inception Mercury 2 40GPT-OSS 120B
100.0%	Gibberish response detection	100Gemini 3.5 Flash Lite (Reasoning) 100GPT-5.5 (Reasoning, Low) 100GPT-5.6 Luna	80Nemotron 3 Nano 96Hermes 3 70B 97GPT-4o, Aug. 6th (temp=1)
100.0%	Markdown formatting overuse	100WizardLM 2 8x22b 100Z.AI GLM 5 100GPT-5.6 Terra	49Ministral 3B 80Ministral 3 3B 80Qwen 3 32B
100.0%	Missing dialogue indicators (quotation marks)	100DeepSeek V4 Flash 100Qwen 3.5 27B 100Qwen 3.5 35B	48GPT-5 69Gemini 2.5 Flash Lite (Reasoning) 87Xiaomi MIMO v2.5 Pro
77.9%	Name drop frequency	100DeepSeek V3.1 100GPT-5.1 100Gemini 3.1 Flash Lite (Reasoning)	7GPT-5.2 16Qwen 3.5 35B 17Qwen 3.5 27B
86.0%	Narrator intent-glossing	100GPT-5.6 Luna 100GPT-4o, Aug. 6th (temp=0) 100ByteDance Seed 2.0 Mini	15GPT-5 Nano 24Gemini 2.5 Flash Lite (Reasoning) 31Gemma 4 26B
100.0%	Overuse of "that" (subordinate clause padding)	100Gemini 3.5 Flash Lite (Reasoning) 100Gemini 3.5 Flash (Reasoning) 100ByteDance Seed 1.6	47Mistral Small 3.2 24B 82DeepSeek V4 Pro (Reasoning) 82Thinking Machines Inkling (Reasoning)
100.0%	Paragraph length variance	100Gemini 3.1 Flash Lite (Preview) 100DeepSeek V4 Flash 100Ministral 8B	33Gemini 2.5 Flash Lite (Reasoning) 33Mistral Small 3.2 24B 43Gemini 2.5 Flash Lite
98.8%	Passive voice overuse	100GPT-5.4 Mini 100Qwen 3.5 Flash 100Gemini 3.6 Flash (Reasoning)	77ByteDance Seed 2.0 Mini 88Mistral NeMO 91Gemini 2.5 Flash Lite
97.0%	Past progressive (was/were + -ing) overuse	100GPT-5.5 (Reasoning) 100GPT-5.4 (Reasoning) 100Qwen 3.5 35B	23Z.AI GLM 4.7 23Claude Opus 4.7 (Reasoning) 29Gemma 4 31B
94.2%	Pronoun-first sentence starts	100GPT-5.4 Mini 100GPT-5.6 Luna (Reasoning) 100Gemini 3.6 Flash (Reasoning, Minimal)	1Mistral Small 3.2 24B 9Gemini 3.1 Flash Lite (Reasoning) 23Gemini 3.1 Flash Lite
97.6%	Purple prose (modifier overload)	100GPT-4o, Aug. 6th (temp=0) 100Claude Opus 4.8 (Reasoning) 100MiniMax M3	80Gemini 3 Flash (Preview, Reasoning) 82Gemini 3.1 Pro (Preview) 84Qwen 3.6 27B
100.0%	Repeated phrase echo	100MoonshotAI: Kimi K3 (Reasoning, High) 100MoonshotAI: Kimi K3 (Reasoning, Low) 100GPT-4o Mini (temp=1)	—
100.0%	Sentence length variance	100ByteDance Seed 1.6 Flash 100GPT-5.5 (Reasoning) 100GPT-5.4 Nano	79Mistral Small 3.2 24B 91Qwen 3.6 27B 91Llama 3.1 70B
57.0%	Sentence opener variety	91DeepSeek V3 (2025-03-24) 89Cydonia 24B V4.1 88Gemini 3.5 Flash Lite (Reasoning)	25Mistral Small 3.2 24B 31Qwen 3.5 27B 33Mistral NeMO
40.2%	Subject-first sentence starts	99Qwen3 235B A22B Instruct 2507 96Writer: Palmyra X5 92Claude Opus 5 (Reasoning, Low)	0Inception Mercury 2 0Qwen 3.5 27B 0Qwen 3.5 35B
25.9%	Subordinate conjunction sentence starts	78Cohere Command R+ (Aug. 2024) 78Gemini 2.5 Flash (Reasoning) 72Gemma 3 4B	0Grok 4.5 (Reasoning, Low) 0ByteDance Seed 2.0 Lite 0Nemotron 3 Super
80.5%	Technical jargon density	100Qwen 3.6 Flash 100Qwen 3.5 9B 100GPT-5.6 Sol	8GPT-5 Nano 12Claude Haiku 4.5 19Claude Sonnet 5 (Reasoning)
70.7%	Useless dialogue additions	100Claude Sonnet 4.6 (Reasoning) 100Claude Opus 4.5 100Qwen 3.5 122B	0GPT-OSS 120B 0Gemma 3 4B 0Ministral 3 8B

Bad Writing Habits

Thriller: chase through city streets

Performance Score Distribution (Top 20)

Price-Performance Score Distribution (Top 20)

Most Stable Models (Top 20)

Top Overall Models (Top 20)