Literary fiction: old friends reunite

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
GPT-5.6 Sol	91%
GPT-5.6 Sol (Reasoning)	91%
GPT-5.6 Luna	90%
GPT-5.5	90%
GPT-5.4	89%
GPT-5.6 Terra (Reasoning)	89%
GPT-5.5 (Reasoning, Low)	89%
GPT-5.4 (Reasoning, Low)	89%
GPT-5.6 Terra	89%
GPT-5.5 (Reasoning)	88%
GPT-5.4 (Reasoning)	88%
GPT-5.6 Luna (Reasoning)	88%
GPT-5.4 Mini	88%
GPT-5.4 Mini (Reasoning, Low)	87%
GPT-5.4 Mini (Reasoning)	86%
Claude Opus 5 (Reasoning, Low)	85%
Grok 4.20 (Reasoning)	85%
DeepSeek V3 (2025-03-24)	85%
Qwen3.6 Max Preview	84%
GPT-5.1	84%

	Score	Cost	Time
GPT-5.6 Luna	90%	$0.017	18.1s
GPT-5.4 Mini	88%	$0.018	20.0s
DeepSeek V3 (2025-03-24)	85%	$0.0012	39.8s
GPT-5.6 Luna (Reasoning)	88%	$0.019	22.6s
GPT-5.4 Mini (Reasoning, Low)	87%	$0.018	21.3s
Ministral 8B	83%	$0.0003	12.7s
GPT-5.4 Mini (Reasoning)	86%	$0.030	33.3s
Qwen 3.6 35B	82%	$0.0062	54.2s
Ministral 3 14B	82%	$0.0006	17.7s
Writer: Palmyra X5	83%	$0.011	23.1s
GPT-5.6 Terra (Reasoning)	89%	$0.053	41.4s
ByteDance Seed 1.6 Flash	83%	$0.0013	30.7s
Mistral Medium 3.1	83%	$0.0047	41.0s
Grok 4.20	83%	$0.0083	50.1s
DeepSeek V4 Flash (Reasoning)	81%	$0.0008	39.8s
o4 Mini	81%	$0.017	27.0s
Qwen3 235B A22B Instruct 2507	83%	$0.0011	1.2m
Mistral Small 4	81%	$0.0015	23.5s
Qwen 3.6 Flash	81%	$0.0096	38.9s
Ministral 3B	78%	$0.0001	7.0s

	Score	Cost	Speed	Stability
GPT-5.6 Luna	90%	$0.017	18.1s	87%
GPT-5.4 Mini	88%	$0.018	20.0s	86%
GPT-5.4 Mini (Reasoning, Low)	87%	$0.018	21.3s	85%
GPT-5.6 Luna (Reasoning)	88%	$0.019	22.6s	83%
GPT-5.4 Mini (Reasoning)	86%	$0.030	33.3s	84%
GPT-5.6 Terra (Reasoning)	89%	$0.053	41.4s	84%
Ministral 3 14B	82%	$0.0006	17.7s	79%
DeepSeek V3 (2025-03-24)	85%	$0.0012	39.8s	79%
Ministral 8B	83%	$0.0003	12.7s	78%
GPT-5.6 Terra	89%	$0.071	54.0s	86%
Mistral Medium 3.1	83%	$0.0047	41.0s	79%
Grok 4.20	83%	$0.0083	50.1s	80%
Writer: Palmyra X5	83%	$0.011	23.1s	77%
ByteDance Seed 1.6 Flash	83%	$0.0013	30.7s	77%
DeepSeek V4 Flash (Reasoning)	81%	$0.0008	39.8s	78%
Mistral Small 4	81%	$0.0015	23.5s	75%
GPT-5.6 Sol	91%	$0.117	1.3m	88%
o4 Mini	81%	$0.017	27.0s	78%
Qwen3 235B A22B Instruct 2507	83%	$0.0011	1.2m	78%
Grok 4.3	80%	$0.0059	23.2s	77%

Rank	Model	Avg. Cost	Avg. Time	Stability	# 1	# 2	# 3	# 4	# 5	Total
17	GPT-5.6 Sol	$0.117	1.3m	88%	93	91	90	90	89	91%
21	GPT-5.6 Sol (Reasoning)	$0.118	1.3m	87%	93	93	90	89	88	91%
1	GPT-5.6 Luna	$0.017	18.1s	87%	92	91	90	89	87	90%
99	GPT-5.5	$0.179	2.0m	87%	92	91	89	88	88	90%
22	GPT-5.4	$0.070	2.0m	85%	92	91	89	88	87	89%
6	GPT-5.6 Terra (Reasoning)	$0.053	41.4s	84%	93	92	89	87	86	89%
84	GPT-5.5 (Reasoning, Low)	$0.160	2.1m	88%	90	89	89	89	88	89%
29	GPT-5.4 (Reasoning, Low)	$0.070	1.9m	84%	92	91	88	87	86	89%
10	GPT-5.6 Terra	$0.071	54.0s	86%	91	90	88	88	88	89%
101	GPT-5.5 (Reasoning)	$0.164	2.0m	86%	90	90	89	86	86	88%
122	GPT-5.4 (Reasoning)	$0.125	3.6m	86%	89	89	88	88	87	88%
4	GPT-5.6 Luna (Reasoning)	$0.019	22.6s	83%	93	90	88	86	83	88%
2	GPT-5.4 Mini	$0.018	20.0s	86%	90	89	89	86	85	88%
3	GPT-5.4 Mini (Reasoning, Low)	$0.018	21.3s	85%	90	88	87	86	86	87%
5	GPT-5.4 Mini (Reasoning)	$0.030	33.3s	84%	89	87	87	85	83	86%
70	Claude Opus 5 (Reasoning, Low)	$0.107	1.2m	80%	89	88	86	83	80	85%
27	Grok 4.20 (Reasoning)	$0.019	1.9m	81%	88	86	85	83	80	85%
8	DeepSeek V3 (2025-03-24)	$0.0012	39.8s	79%	91	87	86	80	78	85%
115	Qwen3.6 Max Preview	$0.054	3.9m	82%	85	85	84	83	82	84%
51	GPT-5.1	$0.066	1.5m	83%	85	85	85	83	82	84%
28	Grok 4.5 (Reasoning, Low)	$0.022	1.3m	78%	89	85	84	81	80	84%
11	Mistral Medium 3.1	$0.0047	41.0s	79%	88	83	83	82	81	83%
67	Claude Opus 4.8 (Reasoning, Low)	$0.073	48.6s	75%	90	86	81	81	79	83%
12	Grok 4.20	$0.0083	50.1s	80%	86	84	84	83	80	83%
19	Qwen3 235B A22B Instruct 2507	$0.0011	1.2m	78%	88	85	83	82	79	83%
13	Writer: Palmyra X5	$0.011	23.1s	77%	89	85	84	79	79	83%
126	MoonshotAI: Kimi K3 (Reasoning, High)	$0.055	2.3m	73%	88	88	80	80	78	83%
9	Ministral 8B	$0.0003	12.7s	78%	87	84	83	81	77	83%
79	Qwen3.7 Max	$0.061	2.1m	81%	83	83	83	83	80	83%
14	ByteDance Seed 1.6 Flash	$0.0013	30.7s	77%	88	83	82	81	78	83%
7	Ministral 3 14B	$0.0006	17.7s	79%	85	84	83	82	79	82%
149	MoonshotAI: Kimi K2.6	$0.050	4.6m	76%	86	85	81	80	80	82%
30	Mistral Large 2	$0.013	34.9s	74%	89	85	80	79	78	82%
32	Aion 3.0 Mini	$0.0057	1.6m	79%	84	83	83	81	77	82%
45	MoonshotAI: Kimi K3 (Reasoning, Low)	$0.029	1.2m	78%	85	84	83	80	77	82%
152	Claude Opus 4	$0.190	1.4m	77%	86	84	83	78	77	82%
60	Grok 4.5 (Reasoning, High)	$0.034	1.7m	78%	85	82	81	80	80	82%
48	Qwen 3.6 35B	$0.0062	54.2s	72%	87	86	85	83	67	82%
23	GPT-4.1	$0.017	34.0s	77%	86	81	81	81	78	81%
136	GPT-5	$0.074	2.9m	78%	84	84	82	79	78	81%
16	Mistral Small 4	$0.0015	23.5s	75%	88	82	81	79	78	81%
33	Z.AI GLM 5 Turbo	$0.0093	40.2s	75%	87	85	82	79	75	81%
106	Grok 4.3 (Reasoning)	$0.021	2.4m	74%	87	85	80	79	76	81%
114	Claude Opus 5 (Reasoning)	$0.111	1.2m	78%	83	83	81	80	79	81%
18	o4 Mini	$0.017	27.0s	78%	84	83	83	81	76	81%
15	DeepSeek V4 Flash (Reasoning)	$0.0008	39.8s	78%	84	83	82	79	78	81%
35	Qwen 3.6 Flash	$0.0096	38.9s	75%	89	82	82	77	75	81%
24	Mistral Small 4 (Reasoning)	$0.0024	37.2s	75%	87	82	80	79	77	81%
102	MoonshotAI: Kimi K2.5	$0.016	2.6m	75%	85	84	82	81	74	81%
49	Claude Sonnet 4.5	$0.035	41.2s	77%	86	82	82	78	77	81%
74	Claude Opus 4.8 (Reasoning)	$0.070	46.2s	77%	85	82	82	79	75	81%
75	Claude Opus 5	$0.071	47.2s	77%	84	83	82	80	75	81%
72	Claude Opus 4.7	$0.062	29.0s	74%	86	83	79	78	77	81%
38	Qwen 3 32B	$0.0015	1.4m	78%	83	81	81	80	78	81%
42	o4 Mini High	$0.027	43.2s	77%	84	81	80	80	78	81%
61	Claude Sonnet 4	$0.035	53.9s	75%	85	81	79	78	78	80%
92	Z.AI GLM 5.1	$0.015	1.6m	70%	87	86	79	77	73	80%
25	Muse Spark 1.1 (Reasoning, Minimal)	$0.012	23.3s	76%	83	83	80	79	76	80%
20	Grok 4.3	$0.0059	23.2s	77%	84	80	80	79	77	80%
73	Qwen 3.5 Plus (2026-04-20)	$0.014	1.4m	73%	88	82	82	78	71	80%
37	Ministral 3 8B	$0.0004	13.8s	71%	87	83	78	77	76	80%
131	Gemini 3.1 Pro (Preview)	$0.073	1.3m	72%	89	82	80	76	74	80%
80	Qwen 3.6 27B	$0.017	1.6m	74%	86	82	80	78	74	80%
41	Qwen 3.5 9B	$0.0010	1.2m	77%	82	81	80	79	77	80%
47	MiniMax M2.7	$0.0036	1.4m	77%	81	81	80	79	77	80%
36	GPT-5.4 Nano (Reasoning)	$0.0063	24.9s	74%	85	81	79	78	76	80%
54	Z.AI GLM 5.2 (Reasoning, High)	$0.015	1.3m	77%	82	80	80	80	77	80%
31	DeepSeek V4 Flash	$0.0007	31.4s	75%	85	80	79	79	76	80%
46	Qwen 3.5 Flash	$0.0028	1.2m	76%	82	80	79	79	78	80%
52	MiniMax M2.5	$0.0041	1.1m	75%	84	81	80	78	75	80%
34	Laguna XS 2.1	$0.0003	22.1s	73%	84	82	79	77	75	79%
65	DeepSeek V4 Pro	$0.0063	1.4m	74%	85	81	79	77	75	79%
50	Mistral Large 3	$0.0028	31.2s	72%	86	84	81	73	72	79%
53	Muse Spark 1.1 (Reasoning, Medium)	$0.015	27.3s	73%	85	81	78	76	76	79%
55	Qwen 3.5 27B	$0.012	1.1m	75%	83	79	78	77	77	79%
137	Claude Opus 4.6	$0.081	1.3m	72%	83	83	80	80	69	79%
58	DeepSeek V3 (2024-12-26)	$0.0019	58.2s	73%	82	82	79	76	72	78%
26	GPT-5.4 Nano (Reasoning, Low)	$0.0054	19.1s	77%	80	79	79	76	76	78%
40	Claude Haiku 4.5	$0.010	21.0s	75%	82	79	79	78	74	78%
148	Claude Opus 4.6 (Reasoning)	$0.112	1.8m	74%	81	80	78	78	74	78%
105	MiniMax M3	$0.0043	2.6m	76%	80	79	79	78	76	78%
108	Qwen 3.5 397B A17B	$0.020	2.0m	74%	82	79	79	78	73	78%
78	Gemini 2.5 Pro	$0.043	44.1s	75%	81	80	79	77	73	78%
81	Hermes 3 405B	$0.0020	1.6m	73%	83	80	78	76	73	78%
143	GPT-5.2	$0.076	1.9m	76%	80	79	79	75	75	78%
87	Claude Sonnet 4.6	$0.035	45.3s	72%	82	80	77	77	73	78%
44	Mistral NeMO	$0.0004	19.7s	73%	81	79	78	77	73	78%
56	Qwen 2.5 72B	$0.0008	33.9s	72%	83	80	78	73	73	78%
39	Ministral 3B	$0.0001	7.0s	73%	80	79	79	79	70	78%
121	Claude Opus 4.7 (Reasoning)	$0.078	35.8s	73%	82	80	78	76	72	77%
139	DeepSeek V4 Pro (Reasoning)	$0.012	3.1m	73%	81	77	76	76	76	77%
43	Mistral Small 3.2 24B	$0.0006	22.9s	74%	80	79	78	78	72	77%
57	Xiaomi MIMO v2.5	$0.0062	37.4s	73%	82	78	78	75	74	77%
160	ByteDance Seed 2.0 Mini	$0.0044	4.9m	70%	84	81	78	74	70	77%
83	Aion 2.0	$0.0063	1.5m	74%	81	78	78	75	74	77%
104	Aion 3.0	$0.024	1.2m	72%	80	80	76	75	74	77%
64	Gemini 2.5 Flash Lite	$0.0009	11.6s	68%	83	82	77	75	67	77%
140	ByteDance Seed 1.6	$0.015	2.9m	74%	79	77	76	75	75	77%
120	Z.AI GLM 4.7	$0.010	1.7m	71%	81	78	75	75	72	76%
66	Laguna S 2.1	$0.0005	16.2s	69%	83	81	77	71	70	76%
127	Gemini 3.5 Flash (Reasoning)	$0.047	28.9s	68%	81	80	74	73	73	76%
59	Qwen 3.5 122B	$0.015	36.9s	75%	77	77	77	75	74	76%
112	DeepSeek V3.2	$0.0013	1.1m	67%	82	82	74	73	70	76%
68	GPT-5 Mini	$0.011	43.2s	73%	78	78	76	76	73	76%
138	Claude Opus 4.5	$0.077	1.0m	73%	80	79	78	72	72	76%
86	Gemma 3 27B	$0.0004	1.1m	71%	80	79	76	74	72	76%
76	Z.AI GLM 4.5 Air	$0.0028	35.2s	70%	81	78	75	74	73	76%
103	Claude Sonnet 5 (Reasoning, Low)	$0.029	39.3s	71%	80	79	75	75	72	76%
135	Z.AI GLM 5	$0.0081	1.5m	66%	86	76	74	72	72	76%
63	GPT-5.4 Nano	$0.0057	21.3s	72%	81	76	76	75	71	76%
144	Thinking Machines Inkling	$0.0078	2.6m	70%	81	79	75	73	72	76%
90	Cohere Command R+ (Aug. 2024)	$0.020	52.5s	72%	80	77	77	74	72	76%
155	Claude Sonnet 4.6 (Reasoning)	$0.072	1.7m	66%	85	78	74	71	71	76%
146	ByteDance Seed 2.0 Lite	$0.013	2.4m	68%	83	77	74	73	72	76%
100	Qwen 3.5 35B	$0.016	52.3s	71%	80	79	76	74	70	76%
71	Gemini 3.6 Flash (Reasoning, Minimal)	$0.019	17.5s	72%	79	78	76	73	72	76%
62	Ministral 3 3B	$0.0003	10.1s	70%	80	78	75	72	72	76%
89	Gemini 3.6 Flash (Reasoning)	$0.039	34.1s	74%	77	77	77	74	73	76%
95	Z.AI GLM 4.5	$0.0066	55.8s	71%	79	78	75	74	71	75%
96	Hermes 3 70B	$0.0007	55.2s	70%	79	79	75	73	71	75%
93	Xiaomi MIMO v2.5 Pro	$0.0088	58.7s	71%	78	77	77	76	69	75%
98	Gemini 3.5 Flash Lite (Reasoning, Minimal)	$0.0054	10.8s	66%	83	79	72	71	71	75%
97	WizardLM 2 8x22b	$0.0023	42.7s	69%	82	77	76	70	69	75%
134	Llama 3.1 70B	$0.0023	54.6s	63%	88	74	74	72	67	75%
82	Gemini 3.1 Flash Lite (Reasoning)	$0.0027	20.9s	69%	79	79	75	73	69	75%
156	Thinking Machines Inkling (Reasoning)	$0.034	3.2m	70%	79	77	74	72	72	75%
77	Gemini 3.1 Flash Lite	$0.0027	17.0s	70%	78	77	73	73	72	75%
69	Gemini 2.5 Flash	$0.0065	13.6s	71%	78	77	76	74	69	75%
113	Z.AI GLM 4.7 Flash	$0.0016	1.0m	68%	82	75	75	70	70	74%
85	GPT-4o, Aug. 6th (temp=0)	$0.018	24.5s	72%	77	75	75	73	72	74%
119	DeepSeek-V2 Chat	$0.0019	47.3s	66%	80	78	73	72	67	74%
110	Gemini 3.5 Flash (Reasoning, Minimal)	$0.024	16.1s	68%	81	76	74	70	69	74%
128	Claude Sonnet 5 (Reasoning)	$0.029	39.8s	69%	78	76	76	74	65	74%
117	Gemma 3 12B	$0.0005	47.6s	67%	78	78	74	74	64	74%
107	Qwen 3.5 Plus (2026-02-15)	$0.0052	32.0s	69%	79	76	75	72	67	74%
132	Gemini 2.5 Flash (Reasoning)	$0.012	24.8s	65%	82	75	72	70	69	74%
109	Gemini 3 Flash (Preview)	$0.0069	17.7s	66%	81	77	73	70	68	74%
118	Cydonia 24B V4.1	$0.0014	55.1s	68%	79	77	75	70	67	73%
129	GPT-4o, Aug. 6th (temp=1)	$0.018	34.1s	67%	80	73	72	72	71	73%
88	Gemini 3 Flash (Preview, Reasoning)	$0.010	24.1s	71%	76	75	74	71	71	73%
94	GPT-4o Mini (temp=0)	$0.0012	27.7s	69%	77	74	73	72	71	73%
125	Claude Sonnet 5	$0.025	35.3s	69%	76	76	73	71	70	73%
91	Arcee AI: Trinity Mini	$0.0003	10.5s	68%	77	75	73	73	67	73%
111	Gemini 3.5 Flash Lite (Reasoning)	$0.0055	10.6s	66%	79	77	72	69	68	73%
142	Gemini 2.5 Flash Lite (Reasoning)	$0.0032	43.9s	62%	81	79	71	71	64	73%
124	Z.AI GLM 4.6	$0.0077	57.0s	69%	75	75	72	72	70	73%
116	Gemma 3 4B	$0.0002	19.2s	66%	76	75	71	70	68	72%
154	Gemma 4 26B	$0.0007	2.6m	66%	78	75	73	70	64	72%
123	Gemini 3.1 Flash Lite (Preview)	$0.0027	7.9s	65%	78	74	72	67	66	71%
130	GPT-4o Mini (temp=1)	$0.0012	31.4s	67%	74	74	71	69	67	71%
153	DeepSeek V3.1	$0.0020	2.4m	67%	75	72	72	69	65	70%
147	Gemma 4 31B	$0.0008	1.2m	65%	74	72	69	68	67	70%
133	GPT-4.1 Mini	$0.0024	18.3s	66%	73	72	70	67	67	70%
151	Gemma 4 31B (Reasoning)	$0.0012	1.4m	63%	75	74	69	65	65	69%
150	Gemma 4 26B (Reasoning)	$0.0018	1.7m	66%	70	70	68	68	67	69%
145	GPT-4.1 Nano	$0.0007	12.1s	63%	71	70	67	67	64	68%
141	Inception Mercury 2	$0.0028	7.6s	66%	70	68	68	66	65	67%
159	Nemotron 3 Super	$0.0000	53.0s	57%	77	69	64	64	61	67%
161	GPT-OSS 120B	$0.0019	2.5m	62%	72	68	66	65	63	67%
158	Nemotron 3 Nano	$0.0008	57.0s	59%	72	71	64	63	63	66%
157	GPT-5 Nano	$0.0037	1.2m	63%	70	67	66	65	63	66%
78.46%

Median	Evaluator	Top 3	Flop 3
98.3%	"Not X but Y" pattern overuse	100Gemma 4 31B (Reasoning) 100MiniMax M2.5 100Gemini 3.5 Flash Lite (Reasoning, Minimal)	2GPT-5 Nano 23Thinking Machines Inkling (Reasoning) 32Nemotron 3 Super
56.7%	Adverb-first sentence starts	100GPT-5.4 Mini 100Mistral Small 4 100GPT-5.4 Mini (Reasoning)	0ByteDance Seed 1.6 0ByteDance Seed 2.0 Lite 0Claude Sonnet 5 (Reasoning)
84.2%	Adverbs in dialogue tags	100Qwen3.7 Max 100Claude Opus 5 (Reasoning) 100ByteDance Seed 2.0 Lite	1GPT-4.1 Nano 3Gemini 3.6 Flash (Reasoning) 7GPT-4.1 Mini
83.9%	AI-ism adverb frequency	97ByteDance Seed 2.0 Lite 97ByteDance Seed 1.6 96ByteDance Seed 1.6 Flash	52GPT-4.1 Nano 60Cydonia 24B V4.1 67Laguna S 2.1
100.0%	AI-ism character names	100GPT-4o Mini (temp=0) 100Llama 3.1 70B 100GPT-5.4	68Claude Opus 4 76Claude Sonnet 4 80Claude Opus 4.5
100.0%	AI-ism location names	100Xiaomi MIMO v2.5 100Claude Opus 4.6 (Reasoning) 100Hermes 3 70B	—
56.2%	AI-ism word frequency	92Claude Opus 5 (Reasoning) 91Claude Opus 5 (Reasoning, Low) 90MoonshotAI: Kimi K3 (Reasoning, High)	0GPT-4o Mini (temp=0) 0GPT-4o, Aug. 6th (temp=1) 0GPT-4o, Aug. 6th (temp=0)
100.0%	Cliché density	100Grok 4.5 (Reasoning, Low) 100Qwen 3.5 9B 100Gemini 3.6 Flash (Reasoning, Minimal)	40Gemini 2.5 Flash 60Mistral Small 3.2 24B 67Gemma 3 12B
95.4%	Dialogue tag variety (said vs. fancy)	100Ministral 3 14B 100GPT-5.6 Sol 100GPT-5.6 Sol (Reasoning)	28GPT-4o, Aug. 6th (temp=1) 32Qwen 3.5 Plus (2026-02-15) 34GPT-4o Mini (temp=1)
23.4%	Em-dash & semicolon overuse	100Qwen 3.5 397B A17B 100GPT-5.6 Terra 100GPT-5.6 Sol (Reasoning)	0Grok 4.5 (Reasoning, Low) 0GPT-4.1 Mini 0Claude Haiku 4.5
100.0%	Emotion telling (show vs. tell)	100Claude Haiku 4.5 100Claude Sonnet 4.6 100Gemini 3.5 Flash (Reasoning, Minimal)	86Llama 3.1 70B 90Mistral NeMO 91Hermes 3 405B
98.1%	Filter word density	100GPT-5.5 (Reasoning) 100GPT-5.4 (Reasoning, Low) 100Claude Sonnet 4	22Nemotron 3 Nano 34Inception Mercury 2 49Nemotron 3 Super
100.0%	Gibberish response detection	100Qwen 3.5 Plus (2026-04-20) 100DeepSeek V3.2 100Laguna XS 2.1	52Llama 3.1 70B 80WizardLM 2 8x22b 80Z.AI GLM 4.5
100.0%	Markdown formatting overuse	100Claude Sonnet 5 (Reasoning) 100Gemini 2.5 Flash Lite (Reasoning) 100Gemini 3.1 Flash Lite (Preview)	80Mistral Medium 3.1 90Claude Opus 5 (Reasoning, Low) 98ByteDance Seed 1.6 Flash
100.0%	Missing dialogue indicators (quotation marks)	100GPT-5.4 (Reasoning) 100Grok 4.5 (Reasoning, High) 100Claude Opus 4.8 (Reasoning)	0Qwen3.7 Max 2Qwen3.6 Max Preview 19Qwen 3.5 397B A17B
63.3%	Name drop frequency	100Z.AI GLM 4.6 100Arcee AI: Trinity Mini 100GPT-5 Nano	0GPT-5.6 Luna (Reasoning) 0GPT-5.5 (Reasoning, Low) 0GPT-5.5 (Reasoning)
69.5%	Narrator intent-glossing	100GPT-5.6 Luna (Reasoning) 100GPT-5.6 Sol (Reasoning) 100GPT-5.6 Terra	0Nemotron 3 Nano 2GPT-5 Nano 8GPT-5 Mini
100.0%	Overuse of "that" (subordinate clause padding)	100GPT-5.4 (Reasoning, Low) 100Gemma 3 27B 100o4 Mini High	72ByteDance Seed 2.0 Mini 78Claude Haiku 4.5 79Llama 3.1 70B
100.0%	Paragraph length variance	100GPT-5.5 100MiniMax M2.7 100GPT-4o Mini (temp=0)	65GPT-5 Nano 66Arcee AI: Trinity Mini 73Cohere Command R+ (Aug. 2024)
96.7%	Passive voice overuse	100o4 Mini High 100GPT-4o Mini (temp=0) 100GPT-4o, Aug. 6th (temp=0)	81Claude Sonnet 5 (Reasoning, Low) 86Gemma 4 31B 86Gemma 4 26B (Reasoning)
94.5%	Past progressive (was/were + -ing) overuse	100GPT-5.5 100MoonshotAI: Kimi K3 (Reasoning, Low) 100Qwen 3.6 27B	25Z.AI GLM 4.6 26Claude Sonnet 4.6 30Muse Spark 1.1 (Reasoning, Minimal)
53.0%	Pronoun-first sentence starts	100GPT-5.5 (Reasoning, Low) 100GPT-5.6 Luna (Reasoning) 100GPT-5.4 Mini (Reasoning)	0o4 Mini High 0DeepSeek V3.1 0Gemma 3 4B
95.1%	Purple prose (modifier overload)	100GPT-5.6 Luna 100MoonshotAI: Kimi K2.5 100Nemotron 3 Super	76GPT-4.1 Nano 79GPT-5.4 Mini (Reasoning, Low) 81Gemini 3.5 Flash Lite (Reasoning, Minimal)
100.0%	Repeated phrase echo	100DeepSeek-V2 Chat 100MoonshotAI: Kimi K2.5 100GPT-4.1	—
100.0%	Sentence length variance	100o4 Mini 100Thinking Machines Inkling (Reasoning) 100Z.AI GLM 5.1	96GPT-4o, Aug. 6th (temp=1) 96Llama 3.1 70B 99Cohere Command R+ (Aug. 2024)
48.7%	Sentence opener variety	86GPT-4o, Aug. 6th (temp=1) 85DeepSeek V3 (2025-03-24) 84GPT-4o Mini (temp=1)	32Qwen 3.5 9B 33Gemini 3.1 Flash Lite 33Qwen 3.5 397B A17B
28.3%	Subject-first sentence starts	79Qwen3 235B A22B Instruct 2507 73Mistral Small 4 70GPT-5.5 (Reasoning, Low)	0Qwen 3.5 9B 0ByteDance Seed 1.6 0GPT-OSS 120B
32.7%	Subordinate conjunction sentence starts	82GPT-5.5 80Ministral 3 8B 77Qwen 3.6 35B	0MoonshotAI: Kimi K3 (Reasoning, Low) 0GPT-4o Mini (temp=0) 0Claude Opus 5 (Reasoning)
63.4%	Technical jargon density	100GPT-5.6 Sol 100Qwen 2.5 72B 100GPT-5.6 Terra (Reasoning)	0Nemotron 3 Nano 0Claude Sonnet 5 (Reasoning) 0GPT-5 Nano
71.9%	Useless dialogue additions	100MoonshotAI: Kimi K2.6 100GPT-5.6 Terra (Reasoning) 100Qwen 3.5 397B A17B	0Gemini 2.5 Flash Lite 0Inception Mercury 2 0Gemma 3 4B

Bad Writing Habits

Literary fiction: old friends reunite

Performance Score Distribution (Top 20)

Price-Performance Score Distribution (Top 20)

Most Stable Models (Top 20)

Top Overall Models (Top 20)