Romance: separated couple reunites

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-5.4 (Reasoning, Low)	90%
GPT-5.4 Mini	90%
GPT-5.5	90%
GPT-5.5 (Reasoning, Low)	89%
GPT-5.4 (Reasoning)	89%
GPT-5.4	89%
GPT-5.5 (Reasoning)	88%
Grok 4.20 (Beta, Reasoning)	87%
GPT-5.4 Mini (Reasoning)	87%
GPT-5.1	87%
Mistral Small Creative	86%
GPT-5.4 Mini (Reasoning, Low)	86%
Grok 4.20 (Reasoning)	86%
Claude Opus 4	86%
Grok 4.20	86%
DeepSeek V4 Flash	85%
Qwen 3.6 35B	85%
Qwen 3.6 Flash	85%
DeepSeek V4 Pro (Reasoning)	85%
Qwen 3.5 397B A17B	85%

	Score	Cost	Time
GPT-5.4 Mini	90%	$0.014	15.5s
Mistral Small Creative	86%	$0.0006	9.0s
Mistral Large 3	84%	$0.0026	28.0s
Grok 4.20 (Beta, Reasoning)	87%	$0.046	44.0s
GPT-5.4 (Reasoning, Low)	90%	$0.052	1.4m
GPT-5.4 Mini (Reasoning, Low)	86%	$0.015	16.6s
GPT-5.4 Mini (Reasoning)	87%	$0.021	24.2s
Grok 4.3	84%	$0.0066	41.3s
Qwen 3.6 35B	85%	$0.0063	51.6s
Grok 4.20	86%	$0.0084	54.9s
DeepSeek V4 Flash (Reasoning)	83%	$0.0007	34.4s
Qwen 3.5 122B	84%	$0.016	47.3s
DeepSeek V4 Pro (Reasoning)	85%	$0.0028	1.4m
GPT-5.4	89%	$0.051	1.4m
DeepSeek V4 Flash	85%	$0.0006	29.0s
Ministral 3 14B	84%	$0.0004	9.5s
Qwen 3.6 Flash	85%	$0.011	40.6s
Mistral Small 4	84%	$0.0011	16.9s
Qwen 3.5 Flash	84%	$0.0026	45.9s
Qwen 3.5 35B	84%	$0.016	1.0m

	Score	Consistency	Stability
GPT-5.4 (Reasoning, Low)	90%	99%	90%
GPT-5.4 Mini	90%	98%	88%
GPT-5.5	90%	98%	88%
GPT-5.5 (Reasoning)	88%	98%	87%
GPT-5.4 (Reasoning)	89%	97%	87%
GPT-5.4 Mini (Reasoning)	87%	98%	85%
GPT-5.4 Mini (Reasoning, Low)	86%	98%	84%
GPT-5.5 (Reasoning, Low)	89%	94%	84%
GPT-5.4	89%	94%	83%
Mistral Small Creative	86%	96%	83%
Grok 4.20 (Beta, Reasoning)	87%	93%	83%
GPT-5.1	87%	96%	83%
Grok 4.20 (Reasoning)	86%	95%	83%
Claude Opus 4	86%	96%	82%
Qwen 3.5 397B A17B	85%	98%	82%
o4 Mini High	84%	98%	82%
Qwen3.7 Max	83%	98%	82%
Qwen 3.5 Flash	84%	97%	82%
Qwen 3.6 35B	85%	95%	82%
Gemini 3.1 Pro (Preview)	83%	97%	81%

	Score	Cost	Speed	Stability
GPT-5.4 Mini	90%	$0.014	15.5s	88%
Mistral Small Creative	86%	$0.0006	9.0s	83%
GPT-5.4 (Reasoning, Low)	90%	$0.052	1.4m	90%
GPT-5.4 Mini (Reasoning, Low)	86%	$0.015	16.6s	84%
GPT-5.4 Mini (Reasoning)	87%	$0.021	24.2s	85%
DeepSeek V4 Flash	85%	$0.0006	29.0s	80%
Qwen 3.6 35B	85%	$0.0063	51.6s	82%
Qwen 3.5 Flash	84%	$0.0026	45.9s	82%
Mistral Small 4	84%	$0.0011	16.9s	80%
Ministral 3 14B	84%	$0.0004	9.5s	79%
Grok 4.20	86%	$0.0084	54.9s	80%
Grok 4.20 (Beta, Reasoning)	87%	$0.046	44.0s	83%
ByteDance Seed 1.6 Flash	84%	$0.0012	28.0s	79%
DeepSeek V4 Pro (Reasoning)	85%	$0.0028	1.4m	81%
GPT-5.4	89%	$0.051	1.4m	83%
o4 Mini High	84%	$0.021	39.0s	82%
DeepSeek V3 (2025-03-24)	84%	$0.0013	1.1m	81%
Mistral Large 2	83%	$0.0097	32.4s	80%
Grok 4.20 (Reasoning)	86%	$0.020	2.0m	83%
Grok 4.3	84%	$0.0066	41.3s	78%

Rank	Model	Avg. Cost	Avg. Time	Stability	# 1	# 2	# 3	# 4	# 5	Total
3	GPT-5.4 (Reasoning, Low)	$0.052	1.4m	90%	91	90	90	90	89	90%
1	GPT-5.4 Mini	$0.014	15.5s	88%	91	90	90	89	88	90%
76	GPT-5.5	$0.156	2.0m	88%	91	90	90	89	88	90%
101	GPT-5.5 (Reasoning, Low)	$0.155	2.0m	84%	94	90	89	87	85	89%
35	GPT-5.4 (Reasoning)	$0.080	2.4m	87%	91	90	89	88	86	89%
15	GPT-5.4	$0.051	1.4m	83%	93	91	89	87	83	89%
83	GPT-5.5 (Reasoning)	$0.150	1.9m	87%	90	89	89	88	86	88%
12	Grok 4.20 (Beta, Reasoning)	$0.046	44.0s	83%	90	90	89	87	81	87%
5	GPT-5.4 Mini (Reasoning)	$0.021	24.2s	85%	88	88	87	87	85	87%
29	GPT-5.1	$0.047	1.5m	83%	90	87	87	85	83	87%
2	Mistral Small Creative	$0.0006	9.0s	83%	89	88	87	85	83	86%
4	GPT-5.4 Mini (Reasoning, Low)	$0.015	16.6s	84%	88	87	86	86	84	86%
19	Grok 4.20 (Reasoning)	$0.020	2.0m	83%	90	87	87	85	83	86%
123	Claude Opus 4	$0.175	1.2m	82%	89	87	86	86	82	86%
11	Grok 4.20	$0.0084	54.9s	80%	89	88	86	86	79	86%
6	DeepSeek V4 Flash	$0.0006	29.0s	80%	89	87	84	84	83	85%
7	Qwen 3.6 35B	$0.0063	51.6s	82%	88	87	86	85	81	85%
22	Qwen 3.6 Flash	$0.011	40.6s	77%	90	90	85	83	78	85%
14	DeepSeek V4 Pro (Reasoning)	$0.0028	1.4m	81%	89	88	86	82	81	85%
79	Qwen 3.5 397B A17B	$0.0068	5.4m	82%	87	85	84	84	84	85%
49	Grok 4.3 (Reasoning)	$0.024	2.2m	80%	89	86	84	84	82	85%
75	GPT-5	$0.058	1.8m	78%	89	87	83	82	81	85%
21	Mistral Small 4 (Reasoning)	$0.0019	29.4s	76%	90	88	83	83	79	85%
69	Claude Opus 4.6 (Reasoning)	$0.076	1.3m	80%	88	87	86	82	80	85%
23	Mistral Large	$0.010	27.4s	77%	91	87	83	81	81	85%
26	Mistral Large 3	$0.0026	28.0s	75%	91	91	87	78	75	84%
30	Qwen 3.5 35B	$0.016	1.0m	79%	88	87	84	83	80	84%
38	Qwen 3.5 Plus (2026-04-20)	$0.016	1.7m	80%	88	84	84	84	81	84%
28	Z.AI GLM 5	$0.0073	59.0s	78%	90	83	83	83	82	84%
59	Qwen 3 32B	$0.0015	1.1m	71%	92	92	83	81	73	84%
20	Grok 4.3	$0.0066	41.3s	78%	87	87	86	85	76	84%
8	Qwen 3.5 Flash	$0.0026	45.9s	82%	86	85	84	83	82	84%
41	DeepSeek V4 Pro	$0.0040	1.9m	78%	89	85	83	82	81	84%
9	Mistral Small 4	$0.0011	16.9s	80%	88	84	84	83	82	84%
52	ByteDance Seed 2.0 Lite	$0.012	2.3m	79%	87	86	85	83	77	84%
42	Z.AI GLM 5 Turbo	$0.0085	41.1s	75%	92	85	83	80	79	84%
27	Qwen 3.5 122B	$0.016	47.3s	79%	88	86	86	81	78	84%
16	o4 Mini High	$0.021	39.0s	82%	85	84	84	83	83	84%
13	ByteDance Seed 1.6 Flash	$0.0012	28.0s	79%	88	84	83	82	81	84%
10	Ministral 3 14B	$0.0004	9.5s	79%	88	85	83	81	81	84%
17	DeepSeek V3 (2025-03-24)	$0.0013	1.1m	81%	86	84	84	82	82	84%
88	Qwen3.7 Max	$0.069	2.6m	82%	85	84	84	82	82	83%
58	Claude Sonnet 4.5	$0.029	33.6s	75%	92	83	83	80	79	83%
18	Mistral Large 2	$0.0097	32.4s	80%	85	85	83	83	80	83%
102	Qwen3.6 Max Preview	$0.052	3.7m	81%	85	84	83	83	81	83%
40	Writer: Palmyra X5	$0.011	22.3s	76%	89	83	82	81	79	83%
31	Qwen3 235B A22B Instruct 2507	$0.0010	53.3s	78%	87	86	84	79	79	83%
94	Claude Opus 4.6	$0.071	1.1m	77%	89	86	85	78	76	83%
109	Gemini 3.1 Pro (Preview)	$0.110	1.5m	81%	85	84	83	82	80	83%
45	Qwen 3.5 9B	$0.0010	1.4m	77%	88	85	82	81	79	83%
24	o4 Mini	$0.012	22.7s	79%	87	83	83	82	79	83%
25	Xiaomi MIMO v2.5	$0.0053	31.9s	78%	87	83	82	81	81	83%
33	DeepSeek V4 Flash (Reasoning)	$0.0007	34.4s	77%	86	86	84	83	74	83%
39	Qwen 3.5 27B	$0.011	1.2m	80%	85	83	82	82	81	83%
57	Claude 3.5 Sonnet	$0.036	30.1s	77%	87	85	83	80	77	82%
37	Grok 4.20 (Beta)	$0.018	16.4s	78%	86	84	83	79	79	82%
32	Mistral Medium 3.1	$0.0040	36.4s	79%	84	84	84	82	76	82%
84	Claude Opus 4.7 (Reasoning)	$0.061	27.2s	76%	85	85	82	82	76	82%
125	MoonshotAI: Kimi K2.5	$0.022	5.7m	79%	85	81	81	81	81	82%
71	Claude Sonnet 4	$0.028	40.0s	74%	89	83	81	79	77	82%
148	MoonshotAI: Kimi K2.6	$0.063	8.6m	77%	84	84	83	81	75	81%
36	Gemini 3.1 Flash Lite (Reasoning)	$0.0030	19.5s	77%	85	84	81	79	79	81%
81	Z.AI GLM 5.1	$0.017	2.2m	77%	85	85	83	79	76	81%
96	Gemini 3 Pro (Preview)	$0.055	57.9s	76%	87	81	81	80	78	81%
62	MiniMax M2.5	$0.0030	1.3m	75%	87	83	81	80	76	81%
34	GPT-5.4 Nano (Reasoning, Low)	$0.0070	24.9s	79%	83	82	81	80	80	81%
55	DeepSeek V3.2	$0.0011	1.3m	77%	84	83	81	81	76	81%
56	Ministral 8B	$0.0002	7.8s	72%	89	84	81	80	73	81%
89	WizardLM 2 8x22b	$0.0020	2.9m	75%	86	82	80	79	79	81%
91	GPT-5.2	$0.051	1.4m	78%	83	82	81	81	77	81%
46	Gemma 3 27B	$0.0005	47.9s	77%	84	82	80	80	78	81%
64	Claude 3.7 Sonnet	$0.035	40.6s	78%	83	82	81	79	78	81%
50	GPT-5.4 Nano	$0.0074	33.9s	76%	85	81	80	79	79	81%
48	MiniMax M2.7	$0.0046	1.2m	79%	83	82	81	79	79	81%
44	LFM2 24B	$0.0001	19.3s	76%	85	82	82	78	76	81%
43	Grok 4.1 Fast	$0.0017	35.6s	78%	83	81	80	80	79	81%
78	Z.AI GLM 4.6	$0.0058	58.1s	73%	87	83	79	78	76	81%
77	DeepSeek V3 (2024-12-26)	$0.0018	50.4s	72%	86	85	80	79	71	80%
51	Gemini 3.1 Flash Lite (Preview)	$0.0029	9.0s	75%	85	82	80	80	74	80%
60	GPT-4.1	$0.016	43.7s	77%	83	82	81	78	76	80%
90	Claude Opus 4.7	$0.058	27.2s	77%	82	82	79	79	78	80%
65	Xiaomi MIMO v2.5 Pro	$0.0087	57.3s	75%	84	82	80	78	76	80%
47	Stealth: Healer Alpha	$0.0000	26.3s	77%	82	82	82	78	75	80%
87	Gemini 2.5 Pro	$0.035	36.8s	74%	85	81	80	79	74	80%
61	Z.AI GLM 4.5	$0.0049	46.5s	76%	84	80	79	78	77	80%
103	Claude Opus 4.5	$0.069	56.6s	78%	81	80	80	79	77	80%
63	Stealth: Hunter Alpha	$0.0000	1.0m	76%	83	81	80	76	76	79%
145	ByteDance Seed 2.0 Mini	$0.0045	5.1m	63%	91	86	75	73	72	79%
74	Z.AI GLM 4.7	$0.0098	56.1s	76%	83	81	80	77	75	79%
133	Qwen 3.6 27B	$0.031	2.9m	71%	84	84	77	76	74	79%
53	Grok 4 Fast	$0.0016	22.8s	77%	82	79	79	78	77	79%
67	Gemma 4 26B	$0.0008	57.7s	75%	83	80	80	79	74	79%
54	Ministral 3 8B	$0.0004	8.3s	75%	83	80	80	78	75	79%
73	GPT-5 Mini	$0.010	1.2m	77%	81	79	79	79	77	79%
92	Claude Sonnet 4.6 (Reasoning)	$0.031	42.1s	75%	83	80	79	77	75	79%
72	Aion 2.0	$0.0062	1.4m	77%	80	80	80	79	76	79%
66	Qwen 3.5 Plus (2026-02-15)	$0.0052	32.8s	75%	82	80	79	76	75	79%
86	Claude Haiku 4.5	$0.0098	19.9s	71%	86	80	78	77	72	79%
127	Grok 4	$0.054	2.1m	75%	81	80	78	78	75	78%
93	Rocinante 12B	$0.0015	48.0s	71%	83	82	77	76	74	78%
82	Gemini 3 Flash (Preview, Reasoning)	$0.013	31.8s	74%	82	80	79	76	75	78%
95	GPT-4o, May 13th (temp=1)	$0.024	12.8s	73%	82	80	80	79	70	78%
118	Hermes 3 405B	$0.0021	45.8s	66%	87	85	76	75	68	78%
68	GPT-5.4 Nano (Reasoning)	$0.0077	28.5s	76%	80	79	78	77	76	78%
70	GPT-4o Mini (temp=1)	$0.0011	33.7s	75%	81	80	80	76	73	78%
111	Gemma 4 26B (Reasoning)	$0.0012	1.7m	72%	81	81	77	75	74	78%
108	Cohere Command R+ (Aug. 2024)	$0.015	52.9s	72%	84	79	79	73	72	77%
138	ByteDance Seed 1.6	$0.015	2.9m	69%	83	82	76	73	73	77%
80	Ministral 3 3B	$0.0003	6.4s	73%	81	78	76	76	74	77%
85	Ministral 3B	$0.0002	14.6s	72%	82	79	78	74	73	77%
106	Gemma 4 31B (Reasoning)	$0.0013	1.4m	72%	81	78	76	76	74	77%
105	Hermes 3 70B	$0.0006	1.2m	72%	82	79	78	75	71	77%
124	DeepSeek-V2 Chat	$0.0017	1.1m	67%	85	79	74	73	71	77%
97	Gemini 3.1 Flash Lite	$0.0027	11.8s	71%	81	79	76	75	71	77%
130	Llama 3.1 8B	$0.0001	24.9s	62%	89	82	74	70	68	77%
100	Gemini 3.5 Flash (Reasoning, Minimal)	$0.017	11.8s	73%	79	78	76	75	73	76%
115	DeepSeek V3.1	$0.0020	2.1m	74%	78	77	77	75	74	76%
113	Claude Sonnet 4.6	$0.024	32.3s	73%	78	77	76	75	72	76%
117	Arcee AI: Trinity Large (Preview)	$0.0000	52.1s	69%	80	79	74	73	72	76%
128	Gemma 4 31B	$0.0008	2.5m	72%	80	78	77	72	71	76%
112	Qwen 2.5 72B	$0.0006	31.5s	70%	81	76	74	74	73	75%
98	Gemini 2.5 Flash	$0.0047	10.0s	72%	78	77	76	75	71	75%
120	Llama 3.1 Nemotron 70B	$0.0024	29.5s	68%	82	78	74	72	72	75%
99	GPT-4o Mini (temp=0)	$0.0011	33.8s	73%	77	77	76	74	72	75%
107	GPT-4o, May 13th (temp=0)	$0.023	10.7s	73%	77	75	75	74	73	75%
131	GPT-4o, Aug. 6th (temp=1)	$0.016	29.4s	67%	80	80	74	72	69	75%
121	Z.AI GLM 4.7 Flash	$0.0016	59.9s	70%	79	78	73	73	72	75%
150	Gemini 3.5 Flash (Reasoning)	$0.193	1.4m	70%	79	78	74	72	72	75%
110	Mistral NeMO	$0.0003	7.4s	70%	79	77	74	73	72	75%
114	Gemini 3 Flash (Preview)	$0.0083	21.1s	71%	77	76	74	74	71	74%
104	Inception Mercury 2	$0.0025	6.5s	72%	76	76	76	72	70	74%
132	Z.AI GLM 4.5 Air	$0.0030	1.2m	68%	80	75	73	71	71	74%
122	Gemma 3 12B	$0.0003	37.0s	70%	76	75	75	74	67	74%
116	Gemini 2.5 Flash (Reasoning)	$0.012	22.7s	72%	75	74	73	73	72	74%
119	GPT-4.1 Nano	$0.0006	13.6s	69%	76	76	74	73	68	73%
129	GPT-4.1 Mini	$0.0021	15.6s	67%	78	76	73	70	67	73%
126	Stealth: Aurora Alpha	$0.0000	7.4s	67%	78	73	72	72	70	73%
136	Inception Mercury	$0.011	16.0s	67%	77	74	73	70	66	72%
134	Gemini 2.5 Flash Lite (Reasoning)	$0.0030	39.4s	68%	76	74	73	70	66	72%
135	Claude 3 Haiku	$0.0023	11.5s	66%	77	74	71	68	67	71%
142	GPT-5 Nano	$0.0047	1.5m	64%	78	72	69	68	68	71%
143	Llama 3.1 70B	$0.0008	21.5s	60%	80	76	68	67	64	71%
141	GPT-OSS 120B	$0.0014	1.9m	67%	74	71	70	70	68	71%
137	Gemma 3 4B	$0.0002	19.7s	67%	74	74	72	67	66	70%
149	Mistral Small 3.2 24B	$0.0044	3.7m	63%	79	71	70	67	64	70%
144	GPT-4o, Aug. 6th (temp=0)	$0.015	15.4s	63%	74	72	71	69	60	69%
140	Gemini 2.5 Flash Lite	$0.0009	10.3s	65%	74	72	72	69	60	69%
146	Nemotron 3 Super	$0.0000	2.1m	64%	75	71	71	67	61	69%
139	Arcee AI: Trinity Mini	$0.0003	9.4s	67%	71	70	69	67	67	69%
147	Nemotron 3 Nano	$0.0009	1.3m	61%	72	70	66	64	64	67%
79.98%

Median	Evaluator	Top 3	Flop 3
100.0%	"Not X but Y" pattern overuse	100Hermes 3 405B 100Qwen 2.5 72B 100DeepSeek V4 Flash (Reasoning)	21GPT-5 Nano 34Nemotron 3 Super 71Gemma 3 4B
42.3%	Adverb-first sentence starts	97GPT-5.4 Mini 94GPT-5.4 (Reasoning, Low) 94Grok 4.20	0Inception Mercury 2 0Inception Mercury 0ByteDance Seed 1.6
100.0%	Adverbs in dialogue tags	100DeepSeek V3.2 100GPT-4o Mini (temp=0) 100GPT-5.4 Mini (Reasoning, Low)	34Llama 3.1 70B 38Llama 3.1 8B 41Hermes 3 70B
90.2%	AI-ism adverb frequency	100Gemini 3.1 Pro (Preview) 100MoonshotAI: Kimi K2.6 99GPT-5.5	55Claude 3 Haiku 58Mistral Small 3.2 24B 66GPT-4.1 Nano
100.0%	AI-ism character names	100Cohere Command R+ (Aug. 2024) 100Grok 4.3 (Reasoning) 100Grok 4.1 Fast	88Claude Sonnet 4 92GPT-5.5 (Reasoning, Low) 92Writer: Palmyra X5
100.0%	AI-ism location names	100Qwen 3.6 35B 100DeepSeek V4 Flash (Reasoning) 100WizardLM 2 8x22b	—
49.0%	AI-ism word frequency	89ByteDance Seed 2.0 Mini 87Claude Opus 4.7 (Reasoning) 85ByteDance Seed 2.0 Lite	0Llama 3.1 Nemotron 70B 0GPT-4o Mini (temp=0) 0GPT-4o Mini (temp=1)
93.3%	Cliché density	100GPT-5.5 100Gemini 3.1 Flash Lite (Preview) 100Claude Opus 4.7 (Reasoning)	33GPT-4o, Aug. 6th (temp=0) 40Gemini 2.5 Flash Lite 47Qwen 2.5 72B
97.4%	Dialogue tag variety (said vs. fancy)	100ByteDance Seed 1.6 100Claude Opus 4.7 100Qwen 3.6 35B	11Gemini 3.5 Flash (Reasoning, Minimal) 13Hermes 3 70B 24Claude 3 Haiku
57.8%	Em-dash & semicolon overuse	100GPT-5.4 Mini (Reasoning, Low) 100Grok 4.3 (Reasoning) 100Inception Mercury	0Mistral Small 4 0Grok 4.1 Fast 0Claude Opus 4.6
100.0%	Emotion telling (show vs. tell)	100Mistral Large 3 100Ministral 3B 100Nemotron 3 Nano	85GPT-4o, May 13th (temp=0) 89Mistral Small 3.2 24B 90Mistral NeMO
98.8%	Filter word density	100GPT-5.4 Nano 100Hermes 3 405B 100GPT-5.5 (Reasoning)	42Llama 3.1 Nemotron 70B 51Nemotron 3 Nano 61Llama 3.1 70B
100.0%	Gibberish response detection	100Mistral Large 2 100Claude Sonnet 4.6 (Reasoning) 100Mistral Small Creative	72Llama 3.1 8B 81Llama 3.1 70B 99Hermes 3 70B
100.0%	Markdown formatting overuse	100GPT-4o, May 13th (temp=1) 100Mistral Large 100GPT-5.5 (Reasoning, Low)	80Ministral 3B 80Qwen 3.5 9B 100ByteDance Seed 1.6 Flash
100.0%	Missing dialogue indicators (quotation marks)	100Z.AI GLM 5.1 100Grok 4.20 (Beta) 100Ministral 3 8B	71Qwen 3.5 Flash 80Qwen 3.6 Flash 80Qwen 3.5 35B
82.5%	Name drop frequency	100DeepSeek V3.1 100MiniMax M2.7 100Z.AI GLM 4.7 Flash	0GPT-5.4 Nano (Reasoning, Low) 7GPT-5.4 Nano (Reasoning) 8Ministral 3B
86.0%	Narrator intent-glossing	100Gemini 3.5 Flash (Reasoning, Minimal) 100Grok 4.1 Fast 100Grok 4.20 (Beta, Reasoning)	2GPT-5 Nano 11Nemotron 3 Nano 13Nemotron 3 Super
100.0%	Overuse of "that" (subordinate clause padding)	100Qwen3.6 Max Preview 100Gemma 3 4B 100Qwen 3 32B	40ByteDance Seed 2.0 Mini 76Ministral 3 8B 77ByteDance Seed 1.6
100.0%	Paragraph length variance	100Ministral 8B 100Gemma 4 31B (Reasoning) 100Qwen 3.5 Flash	38Inception Mercury 39Arcee AI: Trinity Mini 48Grok 4.3 (Reasoning)
99.6%	Passive voice overuse	100GPT-5.4 Mini (Reasoning, Low) 100Gemma 4 31B 100Nemotron 3 Nano	89ByteDance Seed 2.0 Mini 91ByteDance Seed 1.6 92Claude 3 Haiku
100.0%	Past progressive (was/were + -ing) overuse	100Gemini 3.5 Flash (Reasoning, Minimal) 100Grok 4 100Z.AI GLM 4.6	49Claude Sonnet 4.6 57Claude Opus 4.7 59Claude Sonnet 4.6 (Reasoning)
35.6%	Pronoun-first sentence starts	100Ministral 3B 99Llama 3.1 8B 97Llama 3.1 Nemotron 70B	0GPT-5 0GPT-4o Mini (temp=0) 1Gemini 3.1 Flash Lite
97.6%	Purple prose (modifier overload)	100DeepSeek V3.2 100Qwen 3.6 27B 100Grok 4.1 Fast	81GPT-4.1 Nano 83Gemma 3 4B 84Llama 3.1 8B
100.0%	Repeated phrase echo	100GPT-4.1 Mini 100GPT-4.1 Nano 100Z.AI GLM 4.5 Air	—
100.0%	Sentence length variance	100Hermes 3 70B 100Stealth: Hunter Alpha 100Qwen 3.5 122B	83Inception Mercury 87Stealth: Aurora Alpha 90Inception Mercury 2
49.6%	Sentence opener variety	88Llama 3.1 Nemotron 70B 86GPT-4o, Aug. 6th (temp=1) 84Claude 3.5 Sonnet	27Inception Mercury 31Qwen 3.5 9B 33ByteDance Seed 2.0 Lite
15.6%	Subject-first sentence starts	73Rocinante 12B 66Mistral Small Creative 57Mistral Small 4 (Reasoning)	0Gemma 4 26B 0Gemini 3.1 Pro (Preview) 0Inception Mercury 2
20.0%	Subordinate conjunction sentence starts	73Qwen 3.5 122B 71Claude Sonnet 4 70Gemini 3.1 Flash Lite (Reasoning)	0Gemini 3.5 Flash (Reasoning) 0GPT-4o, Aug. 6th (temp=0) 0Gemma 3 4B
83.6%	Technical jargon density	100Qwen 3.5 27B 100Qwen 3.5 Plus (2026-04-20) 100o4 Mini High	8GPT-5 Nano 21Claude Sonnet 4.6 27Nemotron 3 Nano
60.6%	Useless dialogue additions	100ByteDance Seed 2.0 Lite 100Qwen 3.5 Flash 100Qwen 3.5 9B	0GPT-4o Mini (temp=0) 0Gemini 3.5 Flash (Reasoning) 0Inception Mercury

Bad Writing Habits

Romance: separated couple reunites

Performance Score Distribution (Top 20)

Price-Performance Score Distribution (Top 20)

Most Stable Models (Top 20)

Top Overall Models (Top 20)