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%
GPT-5.6 Terra (Reasoning)	88%
GPT-5.6 Terra	88%
Muse Spark 1.1 (Reasoning, Minimal)	88%
GPT-5.6 Sol	87%
GPT-5.6 Luna	87%
GPT-5.6 Luna (Reasoning)	87%
GPT-5.4 Mini (Reasoning)	87%
GPT-5.6 Sol (Reasoning)	87%
GPT-5.1	87%
Grok 4.5 (Reasoning, High)	86%
MoonshotAI: Kimi K3 (Reasoning, High)	86%
GPT-5.4 Mini (Reasoning, Low)	86%
Grok 4.20 (Reasoning)	86%

	Score	Cost	Time
GPT-5.4 Mini	90%	$0.014	15.5s
Muse Spark 1.1 (Reasoning, Minimal)	88%	$0.011	19.7s
Mistral Large 3	84%	$0.0026	28.0s
GPT-5.6 Luna (Reasoning)	87%	$0.017	17.1s
GPT-5.6 Terra	88%	$0.047	38.3s
GPT-5.6 Luna	87%	$0.017	17.0s
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
GPT-5.6 Terra (Reasoning)	88%	$0.046	36.1s
Qwen 3.6 35B	85%	$0.0063	51.6s
Grok 4.20	86%	$0.0084	54.9s
Muse Spark 1.1 (Reasoning, Medium)	86%	$0.015	27.1s
DeepSeek V4 Flash (Reasoning)	83%	$0.0007	34.4s
Qwen 3.5 122B	84%	$0.016	47.3s
Aion 3.0 Mini	85%	$0.0034	58.6s
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

	Score	Cost	Speed	Stability
GPT-5.4 Mini	90%	$0.014	15.5s	88%
GPT-5.6 Luna (Reasoning)	87%	$0.017	17.1s	86%
GPT-5.4 (Reasoning, Low)	90%	$0.052	1.4m	90%
Muse Spark 1.1 (Reasoning, Minimal)	88%	$0.011	19.7s	83%
GPT-5.6 Luna	87%	$0.017	17.0s	84%
GPT-5.4 Mini (Reasoning)	87%	$0.021	24.2s	85%
GPT-5.4 Mini (Reasoning, Low)	86%	$0.015	16.6s	84%
Muse Spark 1.1 (Reasoning, Medium)	86%	$0.015	27.1s	85%
DeepSeek V4 Flash	85%	$0.0006	29.0s	80%
GPT-5.6 Terra (Reasoning)	88%	$0.046	36.1s	84%
Qwen 3.6 35B	85%	$0.0063	51.6s	82%
Aion 3.0 Mini	85%	$0.0034	58.6s	82%
GPT-5.6 Terra	88%	$0.047	38.3s	84%
Qwen 3.5 Flash	84%	$0.0026	45.9s	82%
Mistral Small 4	84%	$0.0011	16.9s	80%
Grok 4.20	86%	$0.0084	54.9s	80%
Ministral 3 14B	84%	$0.0004	9.5s	79%
DeepSeek V4 Pro (Reasoning)	85%	$0.0028	1.4m	81%
GPT-5.4	89%	$0.051	1.4m	83%
Grok 4.5 (Reasoning, High)	86%	$0.026	1.8m	83%

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%
80	GPT-5.5	$0.156	2.0m	88%	91	90	90	89	88	90%
113	GPT-5.5 (Reasoning, Low)	$0.155	2.0m	84%	94	90	89	87	85	89%
36	GPT-5.4 (Reasoning)	$0.080	2.4m	87%	91	90	89	88	86	89%
19	GPT-5.4	$0.051	1.4m	83%	93	91	89	87	83	89%
94	GPT-5.5 (Reasoning)	$0.150	1.9m	87%	90	89	89	88	86	88%
10	GPT-5.6 Terra (Reasoning)	$0.046	36.1s	84%	92	91	88	86	85	88%
13	GPT-5.6 Terra	$0.047	38.3s	84%	92	89	88	86	84	88%
4	Muse Spark 1.1 (Reasoning, Minimal)	$0.011	19.7s	83%	91	90	87	86	84	88%
74	GPT-5.6 Sol	$0.127	1.4m	85%	89	87	87	87	86	87%
5	GPT-5.6 Luna	$0.017	17.0s	84%	90	88	86	86	85	87%
2	GPT-5.6 Luna (Reasoning)	$0.017	17.1s	86%	88	87	87	87	86	87%
6	GPT-5.4 Mini (Reasoning)	$0.021	24.2s	85%	88	88	87	87	85	87%
57	GPT-5.6 Sol (Reasoning)	$0.106	1.1m	85%	88	88	87	86	86	87%
30	GPT-5.1	$0.047	1.5m	83%	90	87	87	85	83	87%
20	Grok 4.5 (Reasoning, High)	$0.026	1.8m	83%	90	87	87	86	83	86%
40	MoonshotAI: Kimi K3 (Reasoning, High)	$0.043	1.9m	82%	90	88	87	85	82	86%
7	GPT-5.4 Mini (Reasoning, Low)	$0.015	16.6s	84%	88	87	86	86	84	86%
23	Grok 4.20 (Reasoning)	$0.020	2.0m	83%	90	87	87	85	83	86%
137	Claude Opus 4	$0.175	1.2m	82%	89	87	86	86	82	86%
8	Muse Spark 1.1 (Reasoning, Medium)	$0.015	27.1s	85%	87	86	86	85	85	86%
16	Grok 4.20	$0.0084	54.9s	80%	89	88	86	86	79	86%
9	DeepSeek V4 Flash	$0.0006	29.0s	80%	89	87	84	84	83	85%
11	Qwen 3.6 35B	$0.0063	51.6s	82%	88	87	86	85	81	85%
29	Qwen 3.6 Flash	$0.011	40.6s	77%	90	90	85	83	78	85%
18	DeepSeek V4 Pro (Reasoning)	$0.0028	1.4m	81%	89	88	86	82	81	85%
12	Aion 3.0 Mini	$0.0034	58.6s	82%	88	87	85	84	82	85%
64	Qwen 3.5 397B A17B	$0.0068	5.4m	82%	87	85	84	84	84	85%
51	Grok 4.3 (Reasoning)	$0.024	2.2m	80%	89	86	84	84	82	85%
81	GPT-5	$0.058	1.8m	78%	89	87	83	82	81	85%
28	Mistral Small 4 (Reasoning)	$0.0019	29.4s	76%	90	88	83	83	79	85%
79	Claude Opus 4.6 (Reasoning)	$0.076	1.3m	80%	88	87	86	82	80	85%
149	Thinking Machines Inkling (Reasoning)	$0.024	11.4m	81%	88	86	85	82	82	84%
37	Mistral Large 3	$0.0026	28.0s	75%	91	91	87	78	75	84%
34	Qwen 3.5 35B	$0.016	1.0m	79%	88	87	84	83	80	84%
41	Qwen 3.5 Plus (2026-04-20)	$0.016	1.7m	80%	88	84	84	84	81	84%
26	Aion 3.0	$0.019	58.7s	81%	88	85	85	82	82	84%
33	Z.AI GLM 5	$0.0073	59.0s	78%	90	83	83	83	82	84%
62	Qwen 3 32B	$0.0015	1.1m	71%	92	92	83	81	73	84%
27	Grok 4.3	$0.0066	41.3s	78%	87	87	86	85	76	84%
14	Qwen 3.5 Flash	$0.0026	45.9s	82%	86	85	84	83	82	84%
44	DeepSeek V4 Pro	$0.0040	1.9m	78%	89	85	83	82	81	84%
15	Mistral Small 4	$0.0011	16.9s	80%	88	84	84	83	82	84%
54	ByteDance Seed 2.0 Lite	$0.012	2.3m	79%	87	86	85	83	77	84%
50	Z.AI GLM 5 Turbo	$0.0085	41.1s	75%	92	85	83	80	79	84%
31	Qwen 3.5 122B	$0.016	47.3s	79%	88	86	86	81	78	84%
24	o4 Mini High	$0.021	39.0s	82%	85	84	84	83	83	84%
21	ByteDance Seed 1.6 Flash	$0.0012	28.0s	79%	88	84	83	82	81	84%
43	Grok 4.5 (Reasoning, Low)	$0.017	52.7s	79%	88	85	83	82	81	84%
17	Ministral 3 14B	$0.0004	9.5s	79%	88	85	83	81	81	84%
22	DeepSeek V3 (2025-03-24)	$0.0013	1.1m	81%	86	84	84	82	82	84%
100	Qwen3.7 Max	$0.069	2.6m	82%	85	84	84	82	82	83%
63	Claude Sonnet 4.5	$0.029	33.6s	75%	92	83	83	80	79	83%
25	Mistral Large 2	$0.0097	32.4s	80%	85	85	83	83	80	83%
96	Claude Opus 5 (Reasoning)	$0.071	47.3s	78%	89	83	83	82	79	83%
107	Qwen3.6 Max Preview	$0.052	3.7m	81%	85	84	83	83	81	83%
48	Writer: Palmyra X5	$0.011	22.3s	76%	89	83	82	81	79	83%
38	Qwen3 235B A22B Instruct 2507	$0.0010	53.3s	78%	87	86	84	79	79	83%
110	Claude Opus 4.6	$0.071	1.1m	77%	89	86	85	78	76	83%
121	Gemini 3.1 Pro (Preview)	$0.110	1.5m	81%	85	84	83	82	80	83%
49	Qwen 3.5 9B	$0.0010	1.4m	77%	88	85	82	81	79	83%
35	o4 Mini	$0.012	22.7s	79%	87	83	83	82	79	83%
71	Claude Opus 4.8 (Reasoning, Low)	$0.060	39.2s	80%	86	85	85	79	78	83%
32	Xiaomi MIMO v2.5	$0.0053	31.9s	78%	87	83	82	81	81	83%
42	DeepSeek V4 Flash (Reasoning)	$0.0007	34.4s	77%	86	86	84	83	74	83%
46	Qwen 3.5 27B	$0.011	1.2m	80%	85	83	82	82	81	83%
75	Claude Opus 5	$0.068	44.6s	81%	84	84	83	81	80	82%
72	Claude Opus 4.8 (Reasoning)	$0.059	39.4s	80%	85	84	83	81	79	82%
56	MoonshotAI: Kimi K3 (Reasoning, Low)	$0.027	1.2m	79%	84	83	82	82	79	82%
93	Claude Opus 5 (Reasoning, Low)	$0.072	48.8s	80%	84	84	83	81	79	82%
39	Mistral Medium 3.1	$0.0040	36.4s	79%	84	84	84	82	76	82%
102	Claude Opus 4.7 (Reasoning)	$0.061	27.2s	76%	85	85	82	82	76	82%
52	Laguna XS 2.1	$0.0004	16.9s	75%	89	81	81	80	78	82%
126	MoonshotAI: Kimi K2.5	$0.022	5.7m	79%	85	81	81	81	81	82%
86	Claude Sonnet 4	$0.028	40.0s	74%	89	83	81	79	77	82%
155	MoonshotAI: Kimi K2.6	$0.063	8.6m	77%	84	84	83	81	75	81%
47	Gemini 3.1 Flash Lite (Reasoning)	$0.0030	19.5s	77%	85	84	81	79	79	81%
85	Z.AI GLM 5.1	$0.017	2.2m	77%	85	85	83	79	76	81%
67	MiniMax M2.5	$0.0030	1.3m	75%	87	83	81	80	76	81%
106	Thinking Machines Inkling	$0.0055	2.1m	72%	87	86	79	78	77	81%
45	GPT-5.4 Nano (Reasoning, Low)	$0.0070	24.9s	79%	83	82	81	80	80	81%
59	DeepSeek V3.2	$0.0011	1.3m	77%	84	83	81	81	76	81%
65	Ministral 8B	$0.0002	7.8s	72%	89	84	81	80	73	81%
98	WizardLM 2 8x22b	$0.0020	2.9m	75%	86	82	80	79	79	81%
105	GPT-5.2	$0.051	1.4m	78%	83	82	81	81	77	81%
53	Gemma 3 27B	$0.0005	47.9s	77%	84	82	80	80	78	81%
69	Z.AI GLM 5.2 (Reasoning, High)	$0.011	58.8s	76%	85	83	80	79	78	81%
58	GPT-5.4 Nano	$0.0074	33.9s	76%	85	81	80	79	79	81%
55	MiniMax M2.7	$0.0046	1.2m	79%	83	82	81	79	79	81%
70	MiniMax M3	$0.0042	2.3m	78%	83	81	81	79	79	81%
91	Z.AI GLM 4.6	$0.0058	58.1s	73%	87	83	79	78	76	81%
92	DeepSeek V3 (2024-12-26)	$0.0018	50.4s	72%	86	85	80	79	71	80%
60	Gemini 3.1 Flash Lite (Preview)	$0.0029	9.0s	75%	85	82	80	80	74	80%
66	GPT-4.1	$0.016	43.7s	77%	83	82	81	78	76	80%
90	Gemini 3.5 Flash Lite (Reasoning)	$0.0028	5.8s	70%	88	86	82	76	69	80%
112	Claude Opus 4.7	$0.058	27.2s	77%	82	82	79	79	78	80%
73	Xiaomi MIMO v2.5 Pro	$0.0087	57.3s	75%	84	82	80	78	76	80%
108	Gemini 2.5 Pro	$0.035	36.8s	74%	85	81	80	79	74	80%
68	Z.AI GLM 4.5	$0.0049	46.5s	76%	84	80	79	78	77	80%
87	Claude Sonnet 5	$0.022	30.7s	76%	82	81	80	80	74	80%
120	Claude Opus 4.5	$0.069	56.6s	78%	81	80	80	79	77	80%
153	ByteDance Seed 2.0 Mini	$0.0045	5.1m	63%	91	86	75	73	72	79%
83	Z.AI GLM 4.7	$0.0098	56.1s	76%	83	81	80	77	75	79%
141	Qwen 3.6 27B	$0.031	2.9m	71%	84	84	77	76	74	79%
76	Gemma 4 26B	$0.0008	57.7s	75%	83	80	80	79	74	79%
61	Ministral 3 8B	$0.0004	8.3s	75%	83	80	80	78	75	79%
82	GPT-5 Mini	$0.010	1.2m	77%	81	79	79	79	77	79%
109	Claude Sonnet 4.6 (Reasoning)	$0.031	42.1s	75%	83	80	79	77	75	79%
78	Aion 2.0	$0.0062	1.4m	77%	80	80	80	79	76	79%
77	Qwen 3.5 Plus (2026-02-15)	$0.0052	32.8s	75%	82	80	79	76	75	79%
95	Claude Sonnet 5 (Reasoning, Low)	$0.025	33.6s	76%	81	80	79	77	76	79%
111	Claude Haiku 4.5	$0.0098	19.9s	71%	86	80	78	77	72	79%
97	Gemini 3 Flash (Preview, Reasoning)	$0.013	31.8s	74%	82	80	79	76	75	78%
131	Gemini 3.6 Flash (Reasoning)	$0.056	40.0s	74%	83	81	81	74	73	78%
89	Gemini 3.5 Flash Lite (Reasoning, Minimal)	$0.0028	5.7s	73%	84	79	79	75	74	78%
99	Claude Sonnet 5 (Reasoning)	$0.021	42.7s	76%	80	79	79	77	76	78%
134	Hermes 3 405B	$0.0021	45.8s	66%	87	85	76	75	68	78%
84	GPT-5.4 Nano (Reasoning)	$0.0077	28.5s	76%	80	79	78	77	76	78%
88	GPT-4o Mini (temp=1)	$0.0011	33.7s	75%	81	80	80	76	73	78%
122	Gemma 4 26B (Reasoning)	$0.0012	1.7m	72%	81	81	77	75	74	78%
124	Cohere Command R+ (Aug. 2024)	$0.015	52.9s	72%	84	79	79	73	72	77%
145	ByteDance Seed 1.6	$0.015	2.9m	69%	83	82	76	73	73	77%
101	Ministral 3 3B	$0.0003	6.4s	73%	81	78	76	76	74	77%
103	Ministral 3B	$0.0002	14.6s	72%	82	79	78	74	73	77%
104	Gemini 3.6 Flash (Reasoning, Minimal)	$0.015	13.9s	75%	79	78	76	76	76	77%
118	Gemma 4 31B (Reasoning)	$0.0013	1.4m	72%	81	78	76	76	74	77%
119	Hermes 3 70B	$0.0006	1.2m	72%	82	79	78	75	71	77%
139	DeepSeek-V2 Chat	$0.0017	1.1m	67%	85	79	74	73	71	77%
114	Gemini 3.1 Flash Lite	$0.0027	11.8s	71%	81	79	76	75	71	77%
117	Gemini 3.5 Flash (Reasoning, Minimal)	$0.017	11.8s	73%	79	78	76	75	73	76%
125	DeepSeek V3.1	$0.0020	2.1m	74%	78	77	77	75	74	76%
129	Claude Sonnet 4.6	$0.024	32.3s	73%	78	77	76	75	72	76%
140	Gemma 4 31B	$0.0008	2.5m	72%	80	78	77	72	71	76%
128	Qwen 2.5 72B	$0.0006	31.5s	70%	81	76	74	74	73	75%
115	Gemini 2.5 Flash	$0.0047	10.0s	72%	78	77	76	75	71	75%
116	GPT-4o Mini (temp=0)	$0.0011	33.8s	73%	77	77	76	74	72	75%
143	GPT-4o, Aug. 6th (temp=1)	$0.016	29.4s	67%	80	80	74	72	69	75%
135	Z.AI GLM 4.7 Flash	$0.0016	59.9s	70%	79	78	73	73	72	75%
161	Gemini 3.5 Flash (Reasoning)	$0.193	1.4m	70%	79	78	74	72	72	75%
127	Mistral NeMO	$0.0003	7.4s	70%	79	77	74	73	72	75%
132	Laguna S 2.1	$0.0005	18.8s	69%	80	77	74	74	70	75%
130	Gemini 3 Flash (Preview)	$0.0083	21.1s	71%	77	76	74	74	71	74%
123	Inception Mercury 2	$0.0025	6.5s	72%	76	76	76	72	70	74%
146	Cydonia 24B V4.1	$0.0014	55.4s	66%	83	73	72	72	71	74%
144	Z.AI GLM 4.5 Air	$0.0030	1.2m	68%	80	75	73	71	71	74%
138	Gemma 3 12B	$0.0003	37.0s	70%	76	75	75	74	67	74%
133	Gemini 2.5 Flash (Reasoning)	$0.012	22.7s	72%	75	74	73	73	72	74%
136	GPT-4.1 Nano	$0.0006	13.6s	69%	76	76	74	73	68	73%
142	GPT-4.1 Mini	$0.0021	15.6s	67%	78	76	73	70	67	73%
147	Gemini 2.5 Flash Lite (Reasoning)	$0.0030	39.4s	68%	76	74	73	70	66	72%
154	GPT-5 Nano	$0.0047	1.5m	64%	78	72	69	68	68	71%
156	Llama 3.1 70B	$0.0008	21.5s	60%	80	76	68	67	64	71%
152	GPT-OSS 120B	$0.0014	1.9m	67%	74	71	70	70	68	71%
148	Gemma 3 4B	$0.0002	19.7s	67%	74	74	72	67	66	70%
160	Mistral Small 3.2 24B	$0.0044	3.7m	63%	79	71	70	67	64	70%
157	GPT-4o, Aug. 6th (temp=0)	$0.015	15.4s	63%	74	72	71	69	60	69%
151	Gemini 2.5 Flash Lite	$0.0009	10.3s	65%	74	72	72	69	60	69%
158	Nemotron 3 Super	$0.0000	2.1m	64%	75	71	71	67	61	69%
150	Arcee AI: Trinity Mini	$0.0003	9.4s	67%	71	70	69	67	67	69%
159	Nemotron 3 Nano	$0.0009	1.3m	61%	72	70	66	64	64	67%
80.65%

Median	Evaluator	Top 3	Flop 3
100.0%	"Not X but Y" pattern overuse	100DeepSeek V4 Flash (Reasoning) 100Gemini 3.5 Flash (Reasoning, Minimal) 100Claude Sonnet 5 (Reasoning, Low)	21GPT-5 Nano 34Nemotron 3 Super 49Thinking Machines Inkling (Reasoning)
41.8%	Adverb-first sentence starts	97GPT-5.4 Mini 94GPT-5.4 (Reasoning, Low) 94Grok 4.20	0Inception Mercury 2 0GPT-4o Mini (temp=0) 0Gemini 3.1 Pro (Preview)
100.0%	Adverbs in dialogue tags	100Qwen 3.5 9B 100Muse Spark 1.1 (Reasoning, Medium) 100Gemini 2.5 Pro	34Llama 3.1 70B 35Laguna S 2.1 41Hermes 3 70B
90.9%	AI-ism adverb frequency	100Gemini 3.1 Pro (Preview) 100MoonshotAI: Kimi K2.6 100GPT-5.6 Sol (Reasoning)	54Cydonia 24B V4.1 58Mistral Small 3.2 24B 66GPT-4.1 Nano
100.0%	AI-ism character names	100GPT-5.4 100Qwen 3.5 397B A17B 100Qwen 3 32B	88Claude Sonnet 4 92DeepSeek V3.2 92Writer: Palmyra X5
100.0%	AI-ism location names	100Gemma 4 26B 100Aion 3.0 100Grok 4.5 (Reasoning, Low)	—
55.8%	AI-ism word frequency	90Claude Opus 5 (Reasoning, Low) 90Claude Opus 5 89Claude Sonnet 5 (Reasoning)	0GPT-4o Mini (temp=1) 0GPT-4o, Aug. 6th (temp=0) 0GPT-4o Mini (temp=0)
100.0%	Cliché density	100Claude Sonnet 4.5 100GPT-5 Mini 100Claude Opus 4.8 (Reasoning)	33GPT-4o, Aug. 6th (temp=0) 40Gemini 2.5 Flash Lite 47Qwen 2.5 72B
99.5%	Dialogue tag variety (said vs. fancy)	100ByteDance Seed 1.6 100GPT-5.4 100Thinking Machines Inkling	11Gemini 3.5 Flash (Reasoning, Minimal) 13Hermes 3 70B 19Cydonia 24B V4.1
56.3%	Em-dash & semicolon overuse	100GPT-5.6 Sol 100Qwen 3.6 35B 100GPT-5.4 (Reasoning, Low)	0GPT-5 Nano 0GPT-4o, Aug. 6th (temp=1) 0Claude Opus 4.6 (Reasoning)
100.0%	Emotion telling (show vs. tell)	100Qwen 3.5 9B 100GPT-5.5 (Reasoning, Low) 100Gemma 3 4B	89Mistral Small 3.2 24B 90Mistral NeMO 91GPT-4o Mini (temp=1)
99.5%	Filter word density	100Claude Opus 4.7 (Reasoning) 100DeepSeek V3 (2024-12-26) 100Qwen 3.5 9B	51Nemotron 3 Nano 61Llama 3.1 70B 64Nemotron 3 Super
100.0%	Gibberish response detection	100Hermes 3 405B 100Qwen 3.6 Flash 100Mistral Medium 3.1	81Llama 3.1 70B 99Hermes 3 70B 99Cydonia 24B V4.1
100.0%	Markdown formatting overuse	100Gemini 2.5 Flash Lite (Reasoning) 100ByteDance Seed 2.0 Lite 100Cohere Command R+ (Aug. 2024)	80Ministral 3B 80Qwen 3.5 9B 100ByteDance Seed 1.6 Flash
100.0%	Missing dialogue indicators (quotation marks)	100Hermes 3 405B 100Gemma 4 26B (Reasoning) 100Claude Opus 5 (Reasoning)	71Qwen 3.5 Flash 80Qwen 3.5 35B 80Qwen 3.6 Flash
84.5%	Name drop frequency	100DeepSeek V3.1 100Claude Opus 4.7 100Claude Opus 5 (Reasoning)	0GPT-5.4 Nano (Reasoning, Low) 7GPT-5.4 Nano (Reasoning) 8Ministral 3B
88.4%	Narrator intent-glossing	100GPT-5.6 Terra (Reasoning) 100Grok 4.3 (Reasoning) 100GPT-4o Mini (temp=1)	2GPT-5 Nano 11Nemotron 3 Nano 13Nemotron 3 Super
100.0%	Overuse of "that" (subordinate clause padding)	100Gemini 3.5 Flash Lite (Reasoning) 100DeepSeek-V2 Chat 100Writer: Palmyra X5	40ByteDance Seed 2.0 Mini 76Ministral 3 8B 77ByteDance Seed 1.6
100.0%	Paragraph length variance	100Aion 2.0 100Claude Opus 4.7 (Reasoning) 100Gemini 2.5 Pro	39Arcee AI: Trinity Mini 48Grok 4.3 (Reasoning) 53Nemotron 3 Nano
99.7%	Passive voice overuse	100o4 Mini 100Gemini 3.1 Pro (Preview) 100GPT-4.1	89ByteDance Seed 2.0 Mini 91ByteDance Seed 1.6 93GPT-4o, Aug. 6th (temp=0)
100.0%	Past progressive (was/were + -ing) overuse	100Gemini 3.5 Flash Lite (Reasoning) 100Qwen 3.5 27B 100Thinking Machines Inkling (Reasoning)	49Claude Sonnet 4.6 57Claude Opus 4.7 57Claude Sonnet 5 (Reasoning)
40.1%	Pronoun-first sentence starts	100Ministral 3B 93Z.AI GLM 5 Turbo 92GPT-5.2	0GPT-5 0GPT-4o Mini (temp=0) 1Gemini 3.1 Flash Lite
97.6%	Purple prose (modifier overload)	100GPT-5 Mini 100Gemma 4 31B 100Inception Mercury 2	51Cydonia 24B V4.1 81GPT-4.1 Nano 83Gemma 3 4B
100.0%	Repeated phrase echo	100Qwen 3.5 35B 100Gemini 2.5 Flash (Reasoning) 100GPT-4o, Aug. 6th (temp=0)	—
100.0%	Sentence length variance	100Qwen 3.5 Flash 100Z.AI GLM 5 100Z.AI GLM 5 Turbo	90Inception Mercury 2 93Grok 4.3 (Reasoning) 95Gemini 3.5 Flash Lite (Reasoning, Minimal)
49.8%	Sentence opener variety	86GPT-4o, Aug. 6th (temp=1) 82Claude Sonnet 4 81Gemini 3.5 Flash Lite (Reasoning)	31Qwen 3.5 9B 33ByteDance Seed 2.0 Lite 33Gemini 3.1 Flash Lite (Preview)
15.6%	Subject-first sentence starts	57Mistral Small 4 (Reasoning) 55Claude Opus 4 54Claude Opus 4.6 (Reasoning)	0Gemini 3.1 Pro (Preview) 0Gemini 3.6 Flash (Reasoning, Minimal) 0Gemma 4 31B
19.2%	Subordinate conjunction sentence starts	73Qwen 3.5 122B 71Claude Sonnet 4 70Gemini 3.1 Flash Lite (Reasoning)	0DeepSeek-V2 Chat 0GPT-4o Mini (temp=0) 0Grok 4.3 (Reasoning)
83.3%	Technical jargon density	100MoonshotAI: Kimi K3 (Reasoning, High) 100Qwen3.6 Max Preview 100Qwen3.7 Max	8GPT-5 Nano 21Claude Sonnet 4.6 23Claude Sonnet 5 (Reasoning)
80.0%	Useless dialogue additions	100Muse Spark 1.1 (Reasoning, Minimal) 100Gemini 3.1 Flash Lite (Reasoning) 100Qwen 3.5 397B A17B	0Gemma 3 12B 0Mistral NeMO 0Gemma 3 4B

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)