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
GPT-5.6 Terra (Reasoning)	92%
GPT-5.4	92%
GPT-5.6 Sol (Reasoning)	91%
GPT-5.4 (Reasoning)	91%
GPT-5.6 Sol	91%
GPT-5.5	91%
GPT-5.4 (Reasoning, Low)	91%
GPT-5.6 Terra	91%
GPT-5.6 Luna (Reasoning)	90%
GPT-5.4 Mini (Reasoning)	90%
Qwen3.6 Max Preview	90%
GPT-5.5 (Reasoning, Low)	90%
GPT-5.5 (Reasoning)	90%
GPT-5.6 Luna	89%
GPT-5.4 Mini	89%
Muse Spark 1.1 (Reasoning, Medium)	88%
Muse Spark 1.1 (Reasoning, Minimal)	88%
Qwen 3.6 27B	87%
GPT-5.4 Mini (Reasoning, Low)	87%
MoonshotAI: Kimi K3 (Reasoning, High)	87%

	Score	Cost	Time
GPT-5.6 Luna (Reasoning)	90%	$0.017	18.2s
GPT-5.4 Mini (Reasoning)	90%	$0.022	26.3s
GPT-5.6 Luna	89%	$0.013	13.0s
GPT-5.4 Mini	89%	$0.015	18.3s
Qwen 3.6 Flash	85%	$0.0085	36.0s
Muse Spark 1.1 (Reasoning, Minimal)	88%	$0.011	20.3s
Muse Spark 1.1 (Reasoning, Medium)	88%	$0.012	22.3s
GPT-5.4 Mini (Reasoning, Low)	87%	$0.013	16.0s
GPT-5.6 Terra (Reasoning)	92%	$0.044	36.0s
Writer: Palmyra X5	86%	$0.011	22.5s
Gemini 2.5 Flash	81%	$0.0039	8.1s
Qwen3 235B A22B Instruct 2507	86%	$0.0011	1.1m
Qwen 3.6 27B	87%	$0.017	1.7m
GPT-5.4	92%	$0.050	1.4m
Gemini 3.5 Flash Lite (Reasoning, Minimal)	84%	$0.0033	6.9s
DeepSeek V4 Flash	81%	$0.0006	27.0s
Mistral Small 4 (Reasoning)	83%	$0.0023	32.8s
Gemini 3.5 Flash Lite (Reasoning)	80%	$0.0032	6.5s
Z.AI GLM 5 Turbo	85%	$0.0068	30.7s
GPT-5.4 (Reasoning, Low)	91%	$0.051	1.4m

	Score	Cost	Speed	Stability
GPT-5.6 Luna	89%	$0.013	13.0s	88%
GPT-5.6 Luna (Reasoning)	90%	$0.017	18.2s	86%
GPT-5.4 Mini	89%	$0.015	18.3s	86%
GPT-5.4 Mini (Reasoning)	90%	$0.022	26.3s	85%
GPT-5.6 Terra (Reasoning)	92%	$0.044	36.0s	88%
Muse Spark 1.1 (Reasoning, Medium)	88%	$0.012	22.3s	83%
GPT-5.4	92%	$0.050	1.4m	90%
GPT-5.4 Mini (Reasoning, Low)	87%	$0.013	16.0s	83%
Muse Spark 1.1 (Reasoning, Minimal)	88%	$0.011	20.3s	81%
GPT-5.6 Terra	91%	$0.051	41.3s	86%
Writer: Palmyra X5	86%	$0.011	22.5s	81%
GPT-5.4 (Reasoning, Low)	91%	$0.051	1.4m	86%
Gemini 3.5 Flash Lite (Reasoning, Minimal)	84%	$0.0033	6.9s	78%
Qwen 3.6 Flash	85%	$0.0085	36.0s	80%
Qwen3 235B A22B Instruct 2507	86%	$0.0011	1.1m	79%
Z.AI GLM 5 Turbo	85%	$0.0068	30.7s	78%
Laguna XS 2.1	82%	$0.0003	16.1s	79%
Qwen 3.5 397B A17B	87%	$0.016	1.5m	82%
GPT-5.6 Sol (Reasoning)	91%	$0.098	1.1m	89%
Qwen 3.6 35B	83%	$0.0053	48.7s	80%

Rank	Model	Avg. Cost	Avg. Time	Stability	# 1	# 2	# 3	# 4	# 5	Total
5	GPT-5.6 Terra (Reasoning)	$0.044	36.0s	88%	96	93	92	92	88	92%
7	GPT-5.4	$0.050	1.4m	90%	94	92	92	91	91	92%
19	GPT-5.6 Sol (Reasoning)	$0.098	1.1m	89%	93	92	92	90	89	91%
42	GPT-5.4 (Reasoning)	$0.086	2.5m	88%	94	93	92	89	87	91%
21	GPT-5.6 Sol	$0.097	1.6m	90%	92	91	91	91	90	91%
115	GPT-5.5	$0.159	1.7m	87%	94	91	90	90	89	91%
12	GPT-5.4 (Reasoning, Low)	$0.051	1.4m	86%	94	94	92	88	86	91%
10	GPT-5.6 Terra	$0.051	41.3s	86%	94	93	90	89	88	91%
2	GPT-5.6 Luna (Reasoning)	$0.017	18.2s	86%	93	92	91	90	86	90%
4	GPT-5.4 Mini (Reasoning)	$0.022	26.3s	85%	94	92	92	87	85	90%
52	Qwen3.6 Max Preview	$0.045	3.3m	83%	93	93	88	87	87	90%
109	GPT-5.5 (Reasoning, Low)	$0.148	1.9m	88%	92	90	89	89	89	90%
84	GPT-5.5 (Reasoning)	$0.130	1.7m	88%	91	90	90	89	88	90%
1	GPT-5.6 Luna	$0.013	13.0s	88%	90	90	90	89	88	89%
3	GPT-5.4 Mini	$0.015	18.3s	86%	92	90	89	88	86	89%
6	Muse Spark 1.1 (Reasoning, Medium)	$0.012	22.3s	83%	93	89	88	86	85	88%
9	Muse Spark 1.1 (Reasoning, Minimal)	$0.011	20.3s	81%	92	90	88	87	81	88%
22	Qwen 3.6 27B	$0.017	1.7m	80%	94	90	90	84	79	87%
8	GPT-5.4 Mini (Reasoning, Low)	$0.013	16.0s	83%	91	88	88	88	82	87%
104	MoonshotAI: Kimi K3 (Reasoning, High)	$0.064	2.6m	80%	93	92	91	81	79	87%
18	Qwen 3.5 397B A17B	$0.016	1.5m	82%	90	89	87	85	82	87%
85	Gemini 3.1 Pro (Preview)	$0.075	1.4m	80%	92	89	88	85	78	86%
11	Writer: Palmyra X5	$0.011	22.5s	81%	90	87	86	86	81	86%
57	Claude Opus 5 (Reasoning, Low)	$0.083	58.1s	83%	89	86	86	85	84	86%
15	Qwen3 235B A22B Instruct 2507	$0.0011	1.1m	79%	92	87	85	83	81	86%
24	Claude Sonnet 4.5	$0.027	34.3s	78%	91	87	84	84	81	85%
61	Grok 4.5 (Reasoning, High)	$0.024	2.3m	78%	92	87	86	82	79	85%
14	Qwen 3.6 Flash	$0.0085	36.0s	80%	90	89	89	82	76	85%
16	Z.AI GLM 5 Turbo	$0.0068	30.7s	78%	91	86	83	83	82	85%
31	MoonshotAI: Kimi K3 (Reasoning, Low)	$0.028	1.2m	80%	89	86	85	83	81	85%
53	Claude Opus 5	$0.075	53.4s	83%	87	85	85	84	83	85%
13	Gemini 3.5 Flash Lite (Reasoning, Minimal)	$0.0033	6.9s	78%	89	87	83	82	81	84%
81	Claude Opus 5 (Reasoning)	$0.080	56.8s	82%	86	86	86	81	81	84%
23	Qwen 3.5 35B	$0.0068	26.9s	76%	90	86	82	81	81	84%
86	Claude Opus 4.8 (Reasoning, Low)	$0.061	42.1s	77%	90	86	83	81	80	84%
20	Qwen 3.6 35B	$0.0053	48.7s	80%	87	84	83	82	81	83%
63	Qwen 3.5 Plus (2026-04-20)	$0.013	1.4m	74%	92	87	85	78	75	83%
102	GPT-5.1	$0.060	1.5m	78%	87	86	84	80	78	83%
92	Qwen3.7 Max	$0.059	1.8m	82%	84	84	83	83	82	83%
32	GPT-4.1	$0.018	46.3s	78%	87	86	85	81	76	83%
89	Claude Opus 4.7	$0.056	28.3s	75%	90	88	86	78	74	83%
41	Z.AI GLM 5.2 (Reasoning, High)	$0.0088	51.7s	75%	90	81	81	81	80	83%
34	Grok 4.5 (Reasoning, Low)	$0.017	50.8s	78%	86	86	83	80	78	83%
58	Gemini 2.5 Pro	$0.038	38.0s	77%	89	83	82	81	79	83%
30	Mistral Small 4 (Reasoning)	$0.0023	32.8s	75%	89	84	83	83	74	83%
142	GPT-5	$0.073	3.0m	80%	85	83	83	83	79	82%
17	Laguna XS 2.1	$0.0003	16.1s	79%	85	84	82	81	80	82%
128	MoonshotAI: Kimi K2.6	$0.035	3.1m	78%	87	86	85	79	76	82%
40	Aion 3.0	$0.017	50.6s	78%	86	83	82	80	78	82%
36	Grok 4.3	$0.0051	25.2s	75%	88	85	83	79	74	82%
75	Claude Sonnet 5	$0.024	34.9s	73%	87	86	80	79	76	82%
65	MiniMax M3	$0.0039	2.3m	78%	85	83	83	80	78	82%
157	Claude Opus 4	$0.181	1.4m	73%	87	85	80	78	76	81%
38	DeepSeek V4 Pro	$0.0043	1.1m	78%	84	84	82	78	78	81%
44	Gemini 2.5 Flash	$0.0039	8.1s	72%	88	86	85	79	68	81%
25	DeepSeek V4 Flash	$0.0006	27.0s	77%	84	83	83	81	75	81%
26	MiniMax M2.5	$0.0026	35.8s	78%	84	83	82	80	77	81%
66	Claude Sonnet 5 (Reasoning)	$0.026	37.9s	75%	86	84	82	80	74	81%
134	Claude Opus 4.6 (Reasoning)	$0.080	1.3m	77%	85	82	81	79	78	81%
37	o4 Mini High	$0.022	37.6s	79%	82	82	81	81	79	81%
56	Gemini 3.5 Flash (Reasoning)	$0.039	24.1s	78%	85	83	83	79	76	81%
76	Hermes 3 405B	$0.0022	1.5m	75%	88	83	83	76	75	81%
82	DeepSeek V3 (2025-03-24)	$0.0012	30.8s	69%	94	81	80	76	73	81%
33	Gemini 2.5 Flash (Reasoning)	$0.0100	19.8s	76%	85	83	81	79	77	81%
27	GPT-4.1 Mini	$0.0025	14.4s	77%	86	81	80	79	79	81%
51	Grok 4.20	$0.0068	40.2s	74%	87	81	80	79	77	81%
108	Claude Opus 4.7 (Reasoning)	$0.063	31.2s	76%	85	84	83	76	75	81%
28	Gemini 2.5 Flash Lite (Reasoning)	$0.0027	28.7s	78%	83	82	81	80	77	81%
62	Aion 3.0 Mini	$0.0044	1.1m	74%	84	84	82	81	71	81%
47	Mistral Medium 3.1	$0.0053	49.4s	76%	84	81	80	79	77	80%
72	DeepSeek-V2 Chat	$0.0015	33.0s	71%	88	85	79	76	75	80%
68	Gemini 3.5 Flash Lite (Reasoning)	$0.0032	6.5s	69%	87	86	82	81	66	80%
121	Claude Opus 4.8 (Reasoning)	$0.063	42.3s	75%	84	84	84	78	72	80%
126	MoonshotAI: Kimi K2.5	$0.016	2.5m	74%	85	83	80	76	75	80%
60	Claude Haiku 4.5	$0.0093	19.7s	73%	86	82	80	80	72	80%
77	DeepSeek V3 (2024-12-26)	$0.0016	36.1s	71%	90	80	80	77	73	80%
73	Z.AI GLM 5.1	$0.012	1.0m	75%	84	82	81	80	73	80%
29	GPT-5.4 Nano (Reasoning, Low)	$0.0049	17.8s	78%	82	82	81	77	77	80%
69	MiniMax M2.7	$0.0034	59.8s	74%	85	80	78	78	78	80%
54	Gemini 3.6 Flash (Reasoning)	$0.027	23.4s	77%	82	82	82	78	75	80%
90	Qwen 3.5 9B	$0.0007	1.0m	71%	86	82	77	77	76	80%
136	GPT-5.2	$0.054	1.5m	73%	86	81	80	79	73	80%
45	o4 Mini	$0.014	22.1s	77%	82	82	80	78	77	80%
39	Qwen 3.5 Flash	$0.0018	44.1s	77%	82	82	81	77	77	80%
46	ByteDance Seed 1.6 Flash	$0.0014	28.9s	75%	83	82	79	78	77	80%
59	Aion 2.0	$0.0049	1.1m	76%	83	81	80	79	75	80%
91	Hermes 3 70B	$0.0006	45.2s	70%	86	85	79	76	72	80%
103	Gemma 3 27B	$0.0004	50.6s	68%	88	85	77	74	74	80%
43	Ministral 3 8B	$0.0003	8.5s	74%	85	79	78	78	77	79%
64	Mistral Small 4	$0.0011	17.2s	71%	87	83	81	78	69	79%
83	Gemini 3.5 Flash (Reasoning, Minimal)	$0.017	11.8s	72%	86	80	78	78	75	79%
35	Ministral 8B	$0.0002	8.4s	75%	83	81	80	77	75	79%
78	Xiaomi MIMO v2.5 Pro	$0.0074	48.8s	74%	84	80	79	77	75	79%
48	Gemini 2.5 Flash Lite	$0.0008	9.4s	74%	84	81	80	77	73	79%
50	GPT-5.4 Nano (Reasoning)	$0.0063	25.1s	75%	82	82	81	77	74	79%
117	Z.AI GLM 5	$0.0067	48.5s	68%	90	80	76	75	74	79%
80	Mistral Large 3	$0.0022	24.1s	71%	84	84	79	78	70	79%
106	Qwen 3.5 27B	$0.0087	47.6s	70%	85	84	77	75	74	79%
119	Claude Sonnet 4.6 (Reasoning)	$0.034	54.3s	73%	83	82	80	79	70	79%
67	DeepSeek V4 Flash (Reasoning)	$0.0006	32.3s	73%	84	82	79	74	74	79%
55	Ministral 3 14B	$0.0005	13.5s	73%	83	82	77	76	75	79%
100	Claude Sonnet 5 (Reasoning, Low)	$0.027	38.4s	74%	84	79	79	76	75	79%
130	Claude Opus 4.5	$0.065	57.5s	77%	80	80	79	79	75	79%
94	GPT-5 Mini	$0.011	42.4s	72%	83	82	77	76	75	79%
101	Mistral Large 2	$0.011	28.8s	70%	85	84	79	75	69	79%
137	Claude Sonnet 4.6	$0.028	37.7s	66%	90	79	76	74	73	78%
129	Claude Sonnet 4	$0.025	38.1s	68%	86	82	75	75	75	78%
70	Gemma 4 31B (Reasoning)	$0.0010	59.4s	75%	82	79	79	76	75	78%
96	GPT-4o, Aug. 6th (temp=1)	$0.015	30.5s	72%	84	82	78	76	73	78%
110	DeepSeek V3.1	$0.0016	1.7m	74%	82	82	81	75	70	78%
87	Z.AI GLM 4.5	$0.0046	39.1s	73%	83	79	78	78	72	78%
79	Xiaomi MIMO v2.5	$0.0045	28.8s	73%	82	82	81	72	72	78%
71	Gemini 3.6 Flash (Reasoning, Minimal)	$0.014	13.7s	74%	82	80	80	75	73	78%
125	WizardLM 2 8x22b	$0.0018	24.7s	65%	90	82	80	76	62	78%
120	Thinking Machines Inkling (Reasoning)	$0.019	41.3s	70%	82	82	76	75	74	78%
49	Gemma 3 4B	$0.0002	19.0s	75%	80	80	79	76	74	78%
131	DeepSeek V3.2	$0.0011	2.8m	75%	81	80	79	75	74	78%
93	GPT-5.4 Nano	$0.0048	18.5s	71%	84	79	77	76	72	78%
145	Claude Opus 4.6	$0.069	1.2m	73%	81	80	79	75	72	77%
135	Cohere Command R+ (Aug. 2024)	$0.021	2.1m	73%	81	78	77	76	75	77%
74	Ministral 3B	$0.0001	5.6s	72%	84	79	78	74	72	77%
99	Thinking Machines Inkling	$0.0072	14.0s	70%	86	80	79	71	70	77%
112	DeepSeek V4 Pro (Reasoning)	$0.0025	1.3m	72%	81	80	79	76	69	77%
114	Z.AI GLM 4.6	$0.0076	35.5s	70%	82	81	75	74	73	77%
116	Gemma 4 26B (Reasoning)	$0.0008	1.7m	73%	80	78	76	75	74	77%
150	Grok 4.3 (Reasoning)	$0.017	2.3m	65%	85	83	75	74	66	77%
98	Mistral NeMO	$0.0005	20.5s	70%	83	77	75	75	73	77%
95	Gemma 3 12B	$0.0002	37.8s	72%	80	78	75	75	75	77%
122	GPT-4.1 Nano	$0.0006	10.0s	66%	87	81	76	70	68	76%
88	Laguna S 2.1	$0.0004	33.9s	74%	79	77	77	76	73	76%
113	Qwen 3.5 122B	$0.012	45.0s	72%	80	78	77	75	71	76%
146	ByteDance Seed 1.6	$0.013	2.6m	71%	80	79	77	75	69	76%
118	Qwen 2.5 72B	$0.0008	39.1s	69%	82	78	75	72	72	76%
107	GPT-4o Mini (temp=1)	$0.0011	23.6s	71%	79	79	76	72	71	76%
97	Qwen 3.5 Plus (2026-02-15)	$0.0049	25.3s	73%	78	77	75	74	74	75%
144	Grok 4.20 (Reasoning)	$0.012	56.5s	65%	84	83	78	69	63	75%
111	Qwen 3 32B	$0.0012	50.5s	73%	77	77	75	74	73	75%
127	Z.AI GLM 4.7 Flash	$0.0015	1.1m	70%	80	77	76	71	71	75%
123	Llama 3.1 70B	$0.0007	23.3s	68%	81	79	79	74	62	75%
105	Arcee AI: Trinity Mini	$0.0003	10.0s	71%	78	76	74	73	71	74%
133	Ministral 3 3B	$0.0003	6.5s	65%	84	75	72	71	70	74%
138	GPT-4o, Aug. 6th (temp=0)	$0.016	21.9s	67%	81	76	73	71	71	74%
148	Cydonia 24B V4.1	$0.0011	41.5s	60%	85	82	72	69	64	74%
152	Gemma 4 31B	$0.0009	2.9m	68%	79	77	75	71	66	74%
124	Gemini 3.1 Flash Lite (Reasoning)	$0.0024	7.6s	69%	78	75	73	71	70	73%
132	Gemini 3.1 Flash Lite	$0.0024	22.6s	69%	76	74	73	72	68	72%
151	Z.AI GLM 4.7	$0.0098	2.0m	68%	77	73	71	71	70	72%
139	GPT-4o Mini (temp=0)	$0.0011	26.3s	68%	76	72	71	70	69	72%
141	Gemini 3 Flash (Preview, Reasoning)	$0.010	24.3s	69%	73	72	71	71	70	71%
140	Gemini 3 Flash (Preview)	$0.0066	17.3s	68%	75	72	72	68	68	71%
158	ByteDance Seed 2.0 Lite	$0.012	2.7m	57%	80	78	66	66	65	71%
143	Nemotron 3 Super	$0.0000	56.8s	69%	72	72	71	69	68	71%
147	Z.AI GLM 4.5 Air	$0.0020	34.3s	65%	75	73	70	68	66	70%
149	Gemini 3.1 Flash Lite (Preview)	$0.0025	7.6s	62%	80	72	70	65	64	70%
159	ByteDance Seed 2.0 Mini	$0.0047	5.3m	63%	75	74	68	67	66	70%
161	Mistral Small 3.2 24B	$0.011	7.1m	67%	71	69	69	68	66	69%
153	Gemma 4 26B	$0.0007	53.0s	64%	71	71	68	65	64	68%
156	GPT-5 Nano	$0.0044	1.6m	64%	68	68	68	66	61	66%
155	Nemotron 3 Nano	$0.0006	1.1m	62%	69	67	65	64	62	66%
154	Inception Mercury 2	$0.0030	8.2s	62%	65	64	63	63	62	63%
160	GPT-OSS 120B	$0.0020	3.3m	59%	67	65	63	63	57	63%
80.00%

Median	Evaluator	Top 3	Flop 3
100.0%	"Not X but Y" pattern overuse	100Arcee AI: Trinity Mini 100Gemini 3.1 Pro (Preview) 100Qwen 3.6 27B	7GPT-5 Nano 30Thinking Machines Inkling 32MoonshotAI: Kimi K2.6
65.5%	Adverb-first sentence starts	100GPT-5.4 (Reasoning, Low) 100Qwen3 235B A22B Instruct 2507 100Claude Opus 4.7	0Inception Mercury 2 2Mistral Small 3.2 24B 5Qwen 3 32B
95.0%	Adverbs in dialogue tags	100Ministral 3 3B 100DeepSeek V4 Flash (Reasoning) 100Claude Opus 4.6	20GPT-5 Nano 31Claude Opus 4 40DeepSeek V3 (2025-03-24)
92.7%	AI-ism adverb frequency	99ByteDance Seed 2.0 Lite 99o4 Mini 98DeepSeek V4 Pro (Reasoning)	81Claude Sonnet 4.6 82Gemma 3 4B 82Laguna S 2.1
100.0%	AI-ism character names	100Grok 4.20 (Reasoning) 100ByteDance Seed 1.6 100Xiaomi MIMO v2.5	92Claude Opus 4 96DeepSeek V4 Pro (Reasoning) 96Laguna S 2.1
100.0%	AI-ism location names	100GPT-4o Mini (temp=1) 100Claude Opus 4.7 100Qwen 3.5 27B	—
50.2%	AI-ism word frequency	91Claude Opus 5 88Claude Opus 4.7 86Claude Opus 5 (Reasoning, Low)	0GPT-4o Mini (temp=0) 0Mistral Small 3.2 24B 1GPT-4o Mini (temp=1)
100.0%	Cliché density	100Claude Opus 5 100GPT-5 Mini 100Z.AI GLM 5 Turbo	33Qwen 2.5 72B 47Mistral Small 3.2 24B 47GPT-4o, Aug. 6th (temp=0)
65.3%	Dialogue tag variety (said vs. fancy)	100GPT-4o, Aug. 6th (temp=0) 100Ministral 8B 100Gemini 2.5 Flash	0Gemma 4 26B 0Gemini 3 Flash (Preview, Reasoning) 1Z.AI GLM 4.7
0.7%	Em-dash & semicolon overuse	100GPT-5.6 Luna (Reasoning) 100Qwen 3.5 397B A17B 100GPT-5.6 Terra	0Claude Sonnet 5 (Reasoning, Low) 0GPT-5.4 Nano 0ByteDance Seed 2.0 Mini
100.0%	Emotion telling (show vs. tell)	100Laguna S 2.1 100Gemini 3.1 Flash Lite (Reasoning) 100MoonshotAI: Kimi K3 (Reasoning, Low)	80WizardLM 2 8x22b 95GPT-4o Mini (temp=1) 96Gemma 4 31B
92.8%	Filter word density	100GPT-5.4 (Reasoning, Low) 100GPT-5.5 (Reasoning, Low) 100GPT-5.4 Mini (Reasoning)	0Nemotron 3 Nano 1Inception Mercury 2 4Nemotron 3 Super
100.0%	Gibberish response detection	100Gemini 3.6 Flash (Reasoning) 100Grok 4.20 (Reasoning) 100Gemini 3.1 Flash Lite (Reasoning)	32WizardLM 2 8x22b 98MiniMax M2.5 99Qwen 3.5 9B
100.0%	Markdown formatting overuse	100DeepSeek-V2 Chat 100Xiaomi MIMO v2.5 100Qwen 3.5 9B	80Ministral 3 3B 80Ministral 3 14B 87Claude Opus 5
100.0%	Missing dialogue indicators (quotation marks)	100GPT-5.4 Nano 100ByteDance Seed 1.6 100GPT-5.4 Mini (Reasoning)	60Qwen 3.5 397B A17B 64Gemini 3.1 Flash Lite (Reasoning) 75Qwen 3.6 Flash
89.4%	Name drop frequency	100Qwen3.6 Max Preview 100Gemini 2.5 Flash (Reasoning) 100Grok 4.5 (Reasoning, High)	27ByteDance Seed 1.6 Flash 37Hermes 3 405B 44GPT-5.6 Luna
79.4%	Narrator intent-glossing	100Ministral 3B 100o4 Mini High 100GPT-5.6 Sol	0Nemotron 3 Nano 1Inception Mercury 2 9GPT-5 Nano
100.0%	Overuse of "that" (subordinate clause padding)	100Inception Mercury 2 100GPT-5.2 100DeepSeek V4 Pro	48Claude Sonnet 5 (Reasoning, Low) 50ByteDance Seed 2.0 Lite 62Claude Sonnet 4.6
99.3%	Paragraph length variance	100Claude Sonnet 5 100Mistral Small 4 (Reasoning) 100GPT-5.4 (Reasoning)	37Grok 4.3 (Reasoning) 38GPT-5 Nano 43ByteDance Seed 2.0 Lite
93.9%	Passive voice overuse	100GPT-5.6 Sol 100GPT-5.5 (Reasoning, Low) 100GPT-5.6 Sol (Reasoning)	83ByteDance Seed 2.0 Lite 84DeepSeek V4 Pro (Reasoning) 85ByteDance Seed 2.0 Mini
80.0%	Past progressive (was/were + -ing) overuse	100GPT-5.6 Luna 100ByteDance Seed 2.0 Lite 100Grok 4.3 (Reasoning)	9Qwen3.7 Max 17Gemma 3 27B 19Z.AI GLM 4.7
82.0%	Pronoun-first sentence starts	100Z.AI GLM 5.1 100GPT-5.6 Terra (Reasoning) 100GPT-5.5	11Mistral Small 3.2 24B 17Gemini 3.1 Flash Lite 22Gemini 3.1 Flash Lite (Reasoning)
97.6%	Purple prose (modifier overload)	100Hermes 3 70B 100Z.AI GLM 4.7 Flash 100ByteDance Seed 1.6 Flash	83Gemini 3.5 Flash (Reasoning) 89Gemini 3.6 Flash (Reasoning, Minimal) 89Gemini 3.6 Flash (Reasoning)
100.0%	Repeated phrase echo	100DeepSeek V4 Pro 100DeepSeek V4 Pro (Reasoning) 100Gemini 3.1 Flash Lite	—
100.0%	Sentence length variance	100Gemma 3 27B 100GPT-4.1 Nano 100DeepSeek V3 (2024-12-26)	82Llama 3.1 70B 92GPT-4o, Aug. 6th (temp=0) 93Grok 4.3 (Reasoning)
50.2%	Sentence opener variety	83WizardLM 2 8x22b 81Cydonia 24B V4.1 81GPT-4o, Aug. 6th (temp=1)	27GPT-5 Nano 27Mistral Small 3.2 24B 31Qwen 3.5 122B
53.1%	Subject-first sentence starts	96GPT-5.4 (Reasoning) 94GPT-5.4 94Claude Opus 5 (Reasoning)	0Inception Mercury 2 3GPT-OSS 120B 11Z.AI GLM 4.7
51.2%	Subordinate conjunction sentence starts	100Gemini 3.5 Flash Lite (Reasoning, Minimal) 100Qwen3.7 Max 100Qwen 3.5 Plus (2026-04-20)	0Mistral Large 3 0WizardLM 2 8x22b 0Claude Opus 5 (Reasoning)
59.2%	Technical jargon density	100GPT-5.6 Sol (Reasoning) 100GPT-5.6 Sol 100Aion 2.0	0Claude Sonnet 5 (Reasoning, Low) 0ByteDance Seed 2.0 Lite 0Nemotron 3 Super
60.0%	Useless dialogue additions	100Gemini 2.5 Flash 100GPT-5.4 Mini (Reasoning) 100Gemini 3.1 Flash Lite (Reasoning)	0Gemma 3 4B 0ByteDance Seed 2.0 Lite 0Arcee AI: Trinity Mini

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)