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-5.4 (Reasoning)	93%
GPT-5.4 (Reasoning, Low)	93%
GPT-5.4	92%
Grok 4.20 (Reasoning)	90%
GPT-5.4 Mini (Reasoning)	90%
GPT-5.5 (Reasoning, Low)	90%
GPT-5.5 (Reasoning)	90%
GPT-5.5	89%
GPT-5.4 Mini (Reasoning, Low)	88%
GPT-5.1	88%
Qwen3.6 Max Preview	88%
Writer: Palmyra X5	88%
Grok 4.20 (Beta, Reasoning)	87%
Z.AI GLM 5 Turbo	87%
Qwen3 235B A22B Instruct 2507	87%
Gemini 3.1 Pro (Preview)	87%
MoonshotAI: Kimi K2.6	87%
Claude Opus 4.7	87%
GPT-5.4 Mini	87%
Qwen 3.5 397B A17B	86%

	Score	Cost	Time
Rocinante 12B	86%	$0.0008	26.2s
Qwen3 235B A22B Instruct 2507	87%	$0.0006	49.7s
GPT-5.4 Mini (Reasoning)	90%	$0.020	29.8s
Writer: Palmyra X5	88%	$0.010	20.5s
Z.AI GLM 5 Turbo	87%	$0.0063	29.9s
GPT-5.4 Mini (Reasoning, Low)	88%	$0.014	16.1s
Mistral Small 4 (Reasoning)	84%	$0.0015	21.5s
Grok 4.1 Fast	85%	$0.0014	23.5s
Mistral Small 4	83%	$0.0009	12.8s
Claude Haiku 4.5	85%	$0.0089	18.4s
MiniMax M2.5	86%	$0.0026	46.1s
Grok 4.20 (Reasoning)	90%	$0.017	1.6m
Gemini 2.5 Flash (Reasoning)	83%	$0.0076	14.4s
GPT-5.4 Mini	87%	$0.012	14.1s
Stealth: Hunter Alpha	84%	$0.0000	47.7s
Qwen 3.5 35B	85%	$0.0086	33.0s
Qwen 3.6 Flash	84%	$0.0092	37.1s
Qwen 3.6 35B	85%	$0.0058	52.0s
Grok 4.20	83%	$0.0078	41.2s
Z.AI GLM 4.7	84%	$0.0095	1.5m

	Score	Consistency	Stability
GPT-5.4	92%	98%	90%
GPT-5.5 (Reasoning)	90%	99%	88%
Grok 4.20 (Reasoning)	90%	98%	88%
GPT-5.5	89%	98%	88%
GPT-5.4 (Reasoning)	93%	95%	88%
GPT-5.4 (Reasoning, Low)	93%	96%	87%
GPT-5.5 (Reasoning, Low)	90%	97%	87%
GPT-5.4 Mini (Reasoning)	90%	96%	86%
Gemini 3.1 Pro (Preview)	87%	98%	85%
GPT-5.4 Mini (Reasoning, Low)	88%	97%	85%
GPT-5.1	88%	95%	85%
Writer: Palmyra X5	88%	97%	84%
Qwen3.6 Max Preview	88%	96%	84%
Grok 4.1 Fast	85%	99%	84%
MoonshotAI: Kimi K2.6	87%	97%	84%
Qwen3.7 Max	85%	98%	84%
GPT-5	85%	98%	84%
Qwen 3.6 27B	86%	97%	83%
GPT-5.4 Mini	87%	96%	83%
Qwen 3.5 35B	85%	96%	82%

	Score	Cost	Speed	Stability
GPT-5.4 Mini (Reasoning)	90%	$0.020	29.8s	86%
GPT-5.4 Mini (Reasoning, Low)	88%	$0.014	16.1s	85%
Writer: Palmyra X5	88%	$0.010	20.5s	84%
Grok 4.20 (Reasoning)	90%	$0.017	1.6m	88%
Grok 4.1 Fast	85%	$0.0014	23.5s	84%
Z.AI GLM 5 Turbo	87%	$0.0063	29.9s	82%
GPT-5.4 Mini	87%	$0.012	14.1s	83%
GPT-5.4	92%	$0.045	1.4m	90%
Qwen3 235B A22B Instruct 2507	87%	$0.0006	49.7s	82%
GPT-5.4 (Reasoning, Low)	93%	$0.046	1.2m	87%
Qwen 3.5 35B	85%	$0.0086	33.0s	82%
Claude Haiku 4.5	85%	$0.0089	18.4s	81%
MiniMax M2.5	86%	$0.0026	46.1s	80%
Mistral Small 4 (Reasoning)	84%	$0.0015	21.5s	80%
Qwen 3.6 35B	85%	$0.0058	52.0s	81%
Mistral Small 4	83%	$0.0009	12.8s	78%
Rocinante 12B	86%	$0.0008	26.2s	75%
Qwen 3.6 Flash	84%	$0.0092	37.1s	80%
Gemini 2.5 Flash Lite	83%	$0.0007	9.0s	77%
Grok 4.20 (Beta)	84%	$0.017	17.9s	81%

Rank	Model	Avg. Cost	Avg. Time	Stability	# 1	# 2	# 3	# 4	# 5	Total
76	GPT-5.4 (Reasoning)	$0.083	2.5m	88%	95	95	92	92	89	93%
10	GPT-5.4 (Reasoning, Low)	$0.046	1.2m	87%	96	94	91	91	91	93%
8	GPT-5.4	$0.045	1.4m	90%	93	93	92	91	91	92%
4	Grok 4.20 (Reasoning)	$0.017	1.6m	88%	91	91	90	89	89	90%
1	GPT-5.4 Mini (Reasoning)	$0.020	29.8s	86%	92	92	90	89	86	90%
120	GPT-5.5 (Reasoning, Low)	$0.127	1.7m	87%	91	91	90	89	87	90%
124	GPT-5.5 (Reasoning)	$0.129	1.8m	88%	91	90	89	89	89	90%
118	GPT-5.5	$0.123	1.7m	88%	90	89	89	88	87	89%
2	GPT-5.4 Mini (Reasoning, Low)	$0.014	16.1s	85%	91	88	88	87	87	88%
60	GPT-5.1	$0.047	2.2m	85%	91	90	89	88	83	88%
105	Qwen3.6 Max Preview	$0.053	3.6m	84%	92	88	88	87	86	88%
3	Writer: Palmyra X5	$0.010	20.5s	84%	90	89	87	87	85	88%
30	Grok 4.20 (Beta, Reasoning)	$0.040	36.0s	80%	93	89	88	87	80	87%
6	Z.AI GLM 5 Turbo	$0.0063	29.9s	82%	90	89	87	86	82	87%
9	Qwen3 235B A22B Instruct 2507	$0.0006	49.7s	82%	90	90	87	86	81	87%
119	Gemini 3.1 Pro (Preview)	$0.105	1.7m	85%	88	87	87	86	86	87%
123	MoonshotAI: Kimi K2.6	$0.049	4.2m	84%	89	88	87	85	84	87%
57	Claude Opus 4.7	$0.059	29.8s	82%	90	89	86	85	82	87%
7	GPT-5.4 Mini	$0.012	14.1s	83%	90	87	86	85	84	87%
95	Qwen 3.5 397B A17B	$0.021	3.3m	79%	91	90	85	83	83	86%
17	Rocinante 12B	$0.0008	26.2s	75%	93	91	87	87	73	86%
13	MiniMax M2.5	$0.0026	46.1s	80%	91	88	86	85	81	86%
22	Qwen 3.6 27B	$0.017	1.7m	83%	88	87	86	86	84	86%
24	Z.AI GLM 5	$0.0062	1.3m	78%	91	88	85	85	80	86%
11	Qwen 3.5 35B	$0.0086	33.0s	82%	88	86	85	85	83	85%
86	Claude Opus 4.7 (Reasoning)	$0.063	30.8s	79%	90	90	87	81	78	85%
109	Qwen3.7 Max	$0.064	2.6m	84%	86	86	85	85	84	85%
12	Claude Haiku 4.5	$0.0089	18.4s	81%	88	88	86	83	81	85%
130	GPT-5	$0.066	3.3m	84%	86	86	86	85	83	85%
23	Claude Sonnet 4.5	$0.028	34.3s	82%	87	86	84	83	83	85%
5	Grok 4.1 Fast	$0.0014	23.5s	84%	85	85	85	85	84	85%
92	Gemini 3.5 Flash (Reasoning)	$0.057	31.1s	77%	91	88	87	83	74	85%
138	Claude Opus 4	$0.123	52.2s	81%	89	85	84	83	82	85%
15	Qwen 3.6 35B	$0.0058	52.0s	81%	87	86	84	84	83	85%
114	Claude Opus 4.6	$0.073	1.3m	79%	89	86	85	83	78	85%
18	Qwen 3.6 Flash	$0.0092	37.1s	80%	87	87	85	83	79	84%
26	Qwen 3.5 122B	$0.015	41.8s	79%	88	84	83	83	82	84%
29	Qwen 3.5 9B	$0.0012	1.5m	79%	87	86	83	82	82	84%
67	Z.AI GLM 4.6	$0.0056	1.1m	71%	93	90	81	80	77	84%
45	Claude Sonnet 4.6	$0.024	36.1s	78%	90	86	85	82	78	84%
47	Z.AI GLM 5.1	$0.0096	1.4m	78%	90	83	83	83	82	84%
34	Aion 2.0	$0.0047	1.1m	78%	88	87	84	82	79	84%
31	Stealth: Hunter Alpha	$0.0000	47.7s	75%	92	84	84	84	75	84%
112	Grok 4.3 (Reasoning)	$0.027	3.1m	78%	89	86	86	81	77	84%
20	Grok 4.20 (Beta)	$0.017	17.9s	81%	87	86	86	81	79	84%
44	Z.AI GLM 4.7	$0.0095	1.5m	80%	87	86	85	81	80	84%
14	Mistral Small 4 (Reasoning)	$0.0015	21.5s	80%	87	86	85	82	79	84%
41	DeepSeek V4 Pro	$0.0035	1.7m	80%	86	85	84	83	80	83%
141	DeepSeek V4 Pro (Reasoning)	$0.015	5.0m	73%	90	88	81	80	77	83%
28	Z.AI GLM 4.7 Flash	$0.0017	1.3m	80%	86	83	83	82	82	83%
39	GPT-4.1	$0.016	51.3s	80%	85	85	83	83	79	83%
16	Mistral Small 4	$0.0009	12.8s	78%	88	85	84	79	78	83%
42	Gemini 2.5 Flash (Reasoning)	$0.0076	14.4s	74%	89	86	85	83	71	83%
27	Grok 4.20	$0.0078	41.2s	79%	86	86	84	79	78	83%
54	o4 Mini High	$0.025	47.6s	80%	84	84	84	83	78	83%
63	Gemma 4 26B (Reasoning)	$0.0019	1.7m	77%	89	84	83	79	78	83%
46	Xiaomi MIMO v2.5 Pro	$0.0068	45.2s	76%	88	84	84	83	75	83%
108	Qwen 3.5 Plus (2026-04-20)	$0.020	2.1m	73%	90	87	81	79	77	83%
19	Gemini 2.5 Flash Lite	$0.0007	9.0s	77%	87	85	81	81	79	83%
71	Qwen 3.5 27B	$0.013	1.1m	75%	89	84	81	80	79	83%
83	ByteDance Seed 2.0 Lite	$0.011	2.2m	78%	87	85	84	80	77	82%
33	MiniMax M2.7	$0.0028	1.1m	79%	86	83	83	81	80	82%
32	Grok 4.3	$0.0056	32.1s	77%	87	83	81	81	80	82%
38	Qwen 3.5 Flash	$0.0017	40.7s	76%	87	84	81	81	78	82%
107	MoonshotAI: Kimi K2.5	$0.024	3.1m	80%	84	83	83	83	79	82%
113	Claude Opus 4.6 (Reasoning)	$0.071	1.2m	81%	83	83	83	82	80	82%
21	Gemma 4 26B	$0.0007	28.4s	78%	85	84	82	80	79	82%
90	Gemma 4 31B (Reasoning)	$0.0013	2.7m	78%	86	83	82	81	78	82%
37	Gemma 3 27B	$0.0005	43.7s	77%	86	83	81	81	79	82%
127	Claude Opus 4.5	$0.070	1.0m	78%	85	84	81	81	79	82%
65	Gemini 2.5 Pro	$0.030	31.4s	79%	85	83	83	79	78	82%
35	Mistral Medium 3.1	$0.0041	30.6s	78%	85	84	83	81	76	82%
48	Mistral Large 2	$0.0088	23.3s	76%	85	84	81	79	77	81%
25	GPT-5.4 Nano (Reasoning, Low)	$0.0055	22.0s	79%	83	81	81	81	80	81%
40	Mistral Large	$0.0080	20.9s	77%	85	82	80	80	79	81%
74	DeepSeek V3.1	$0.0017	1.3m	74%	86	83	80	78	77	81%
59	Gemini 3.5 Flash (Reasoning, Minimal)	$0.015	10.8s	75%	85	84	80	79	77	81%
50	GPT-5.4 Nano (Reasoning)	$0.0063	27.0s	76%	86	82	80	79	78	81%
85	WizardLM 2 8x22b	$0.0017	1.9m	76%	85	83	81	80	75	81%
64	GPT-5 Mini	$0.0095	1.0m	77%	83	83	81	81	76	81%
53	Mistral Small Creative	$0.0005	7.8s	72%	87	84	80	78	75	81%
52	Mistral Large 3	$0.0022	21.9s	74%	85	84	79	79	77	81%
72	ByteDance Seed 1.6 Flash	$0.0011	23.2s	71%	90	80	78	77	77	80%
55	o4 Mini	$0.014	27.2s	78%	82	82	81	79	78	80%
80	DeepSeek-V2 Chat	$0.0015	48.1s	71%	87	84	80	79	72	80%
62	Qwen 3.5 Plus (2026-02-15)	$0.0058	31.6s	75%	84	83	80	80	74	80%
61	DeepSeek V4 Flash	$0.0005	24.0s	73%	86	83	80	77	74	80%
56	DeepSeek V4 Flash (Reasoning)	$0.0005	24.9s	74%	86	82	82	77	73	80%
43	Gemini 3.1 Flash Lite (Reasoning)	$0.0025	9.0s	76%	84	80	80	77	77	80%
88	DeepSeek V3.2	$0.0009	1.3m	73%	86	82	80	78	74	80%
94	Gemma 4 31B	$0.0008	1.7m	75%	84	79	79	78	78	80%
131	GPT-5.2	$0.047	1.4m	75%	84	80	79	77	77	79%
36	Gemini 3.1 Flash Lite (Preview)	$0.0023	6.9s	78%	81	81	80	78	77	79%
78	Xiaomi MIMO v2.5	$0.0046	28.2s	72%	87	80	79	76	75	79%
136	Gemini 3 Pro (Preview)	$0.069	1.2m	75%	82	81	80	78	75	79%
70	DeepSeek V3 (2025-03-24)	$0.0010	1.1m	77%	82	81	81	76	76	79%
49	GPT-4.1 Nano	$0.0006	10.8s	76%	82	81	80	78	74	79%
51	Ministral 3 14B	$0.0004	8.9s	75%	82	81	81	77	73	79%
84	Gemini 2.5 Flash	$0.0037	8.5s	69%	86	83	79	79	68	79%
69	Gemma 3 12B	$0.0003	41.6s	75%	82	81	79	77	75	79%
104	Claude 3.5 Sonnet	$0.032	30.8s	74%	82	81	79	79	72	79%
66	Ministral 8B	$0.0002	8.6s	72%	83	80	77	76	75	78%
103	GPT-5.4 Nano	$0.0061	1.9m	75%	81	80	78	76	76	78%
106	DeepSeek V3 (2024-12-26)	$0.0018	1.4m	70%	86	78	76	76	76	78%
58	Ministral 3 3B	$0.0002	3.3s	74%	82	79	78	77	74	78%
81	Qwen 3 32B	$0.0012	47.9s	74%	82	80	78	77	74	78%
75	Gemini 3.1 Flash Lite	$0.0027	17.6s	73%	82	81	78	77	72	78%
129	Claude Sonnet 4.6 (Reasoning)	$0.030	41.4s	69%	87	78	77	75	73	78%
79	GPT-4.1 Mini	$0.0024	22.4s	73%	83	78	77	75	75	78%
115	Hermes 3 70B	$0.0009	2.0m	72%	84	79	78	76	72	78%
111	Cohere Command R+ (Aug. 2024)	$0.016	45.2s	70%	83	82	77	76	71	78%
91	Grok 4 Fast	$0.0016	26.5s	71%	84	81	78	75	71	78%
96	GPT-4o, May 13th (temp=0)	$0.027	12.8s	75%	80	79	78	76	75	78%
100	GPT-4o, Aug. 6th (temp=1)	$0.017	20.8s	73%	82	80	77	75	74	78%
99	Z.AI GLM 4.5	$0.0043	47.5s	72%	84	78	77	75	74	78%
73	LFM2 24B	$0.0002	22.8s	74%	81	78	77	76	75	77%
98	Gemini 2.5 Flash Lite (Reasoning)	$0.0019	19.2s	69%	88	79	79	71	71	77%
77	Ministral 3 8B	$0.0004	8.5s	72%	83	79	77	74	74	77%
102	Stealth: Healer Alpha	$0.0000	22.1s	68%	87	81	80	69	68	77%
93	Claude 3 Haiku	$0.0020	11.8s	70%	84	76	75	75	75	77%
110	GPT-4o, Aug. 6th (temp=0)	$0.017	22.3s	70%	85	78	77	74	72	77%
82	Arcee AI: Trinity Mini	$0.0003	8.6s	71%	82	79	78	73	71	77%
68	Mistral NeMO	$0.0004	9.2s	75%	78	78	77	76	74	77%
116	Claude Sonnet 4	$0.024	36.4s	72%	80	78	77	76	72	76%
89	Ministral 3B	$0.0001	2.7s	70%	82	78	75	74	74	76%
150	Mistral Small 3.2 24B	$0.0042	6.3m	73%	80	79	78	74	71	76%
97	GPT-4o Mini (temp=1)	$0.0010	35.8s	72%	79	78	75	74	74	76%
117	Z.AI GLM 4.5 Air	$0.0021	59.3s	69%	81	80	75	73	72	76%
87	Gemma 3 4B	$0.0002	21.6s	73%	80	76	75	75	75	76%
143	Grok 4	$0.046	1.7m	71%	81	76	76	74	71	76%
125	GPT-4o, May 13th (temp=1)	$0.029	15.7s	71%	81	78	77	72	70	76%
140	ByteDance Seed 1.6	$0.014	2.7m	71%	80	76	75	73	73	76%
101	Hermes 3 405B	$0.0018	23.8s	71%	79	78	76	73	70	75%
121	Llama 3.1 8B	$0.0001	34.7s	66%	86	76	75	70	69	75%
126	Gemini 3 Flash (Preview)	$0.011	29.5s	68%	83	76	75	73	69	75%
137	Claude 3.7 Sonnet	$0.031	38.7s	67%	81	78	73	73	71	75%
133	Arcee AI: Trinity Large (Preview)	$0.0000	48.5s	65%	85	76	72	71	70	75%
122	Gemini 3 Flash (Preview, Reasoning)	$0.014	34.4s	70%	78	77	76	75	67	75%
149	ByteDance Seed 2.0 Mini	$0.0043	4.8m	68%	80	79	75	73	66	75%
128	Qwen 2.5 72B	$0.0008	45.0s	68%	80	76	73	72	70	74%
132	GPT-4o Mini (temp=0)	$0.0010	36.0s	67%	79	74	72	71	67	73%
135	Llama 3.1 70B	$0.0008	25.0s	65%	79	77	72	69	65	72%
139	GPT-5 Nano	$0.0037	1.3m	66%	77	74	71	70	67	72%
145	Nemotron 3 Super	$0.0000	2.4m	68%	75	74	73	68	65	71%
142	Llama 3.1 Nemotron 70B	$0.0024	28.4s	62%	78	71	68	67	65	70%
134	Inception Mercury 2	$0.0023	5.7s	68%	71	70	70	69	68	69%
146	GPT-OSS 120B	$0.0014	1.6m	65%	72	71	69	67	64	68%
148	Nemotron 3 Nano	$0.0007	40.2s	56%	82	69	65	64	61	68%
147	Inception Mercury	$0.012	17.7s	61%	71	71	66	64	61	67%
144	Stealth: Aurora Alpha	$0.0000	8.1s	62%	70	70	66	64	62	66%
80.87%

Median	Evaluator	Top 3	Flop 3
100.0%	"Not X but Y" pattern overuse	100Qwen3.7 Max 100Gemma 4 26B (Reasoning) 100GPT-4o Mini (temp=0)	50DeepSeek V3.2 60DeepSeek V4 Pro (Reasoning) 66Claude Opus 4.6
48.3%	Adverb-first sentence starts	100Claude Opus 4.7 98Writer: Palmyra X5 97Ministral 3 14B	0Nemotron 3 Nano 0GPT-OSS 120B 0Gemma 4 31B (Reasoning)
100.0%	Adverbs in dialogue tags	100Gemini 2.5 Flash 100Writer: Palmyra X5 100GPT-5.4 Nano (Reasoning, Low)	60Hermes 3 405B 66GPT-4.1 Nano 67DeepSeek V3 (2025-03-24)
94.7%	AI-ism adverb frequency	100GPT-5.5 100GPT-5.5 (Reasoning) 100MoonshotAI: Kimi K2.6	77GPT-4.1 Nano 78Claude 3 Haiku 82Claude 3.7 Sonnet
100.0%	AI-ism character names	100Qwen 3.5 Plus (2026-02-15) 100Z.AI GLM 4.5 100Gemini 3.1 Flash Lite (Reasoning)	92Llama 3.1 8B 92Gemma 3 12B 92Gemma 3 4B
100.0%	AI-ism location names	100Mistral Small 4 100ByteDance Seed 2.0 Mini 100Qwen3 235B A22B Instruct 2507	—
42.5%	AI-ism word frequency	86GPT-5.4 (Reasoning) 82GPT-5.5 (Reasoning) 82Claude Sonnet 4.6	0Gemini 2.5 Flash Lite (Reasoning) 0Stealth: Aurora Alpha 0GPT-4o, Aug. 6th (temp=0)
100.0%	Cliché density	100Claude Opus 4 100Z.AI GLM 5 100Claude Sonnet 4.6	13GPT-4o, May 13th (temp=0) 20Qwen 2.5 72B 33Stealth: Aurora Alpha
80.0%	Dialogue tag variety (said vs. fancy)	100Claude 3.5 Sonnet 100Qwen 3.5 9B 100Gemma 4 26B	0Rocinante 12B 0GPT-4o Mini (temp=1) 0GPT-4o Mini (temp=0)
31.0%	Em-dash & semicolon overuse	100Qwen 3.6 27B 100Qwen 3.5 122B 100Inception Mercury	0Grok 4.1 Fast 0Grok 4 0DeepSeek V4 Pro (Reasoning)
100.0%	Emotion telling (show vs. tell)	100Gemma 4 26B 100Ministral 3 8B 100Qwen3 235B A22B Instruct 2507	87Llama 3.1 70B 90GPT-4.1 Mini 92Hermes 3 70B
96.1%	Filter word density	100Gemini 3.1 Pro (Preview) 100Qwen3.7 Max 100Grok 4.1 Fast	21Claude Sonnet 4 27Stealth: Aurora Alpha 42GPT-OSS 120B
100.0%	Gibberish response detection	100ByteDance Seed 2.0 Lite 100Z.AI GLM 4.5 100GPT-4o, May 13th (temp=0)	40Llama 3.1 8B 99ByteDance Seed 1.6 Flash 99MiniMax M2.5
100.0%	Markdown formatting overuse	100Gemini 3.5 Flash (Reasoning, Minimal) 100Nemotron 3 Super 100ByteDance Seed 2.0 Lite	60Ministral 3B 80Ministral 3 8B 82Ministral 3 14B
100.0%	Missing dialogue indicators (quotation marks)	100DeepSeek V4 Flash (Reasoning) 100Stealth: Healer Alpha 100Ministral 3 14B	80Qwen 3.6 Flash 81Grok 4 Fast 88Rocinante 12B
74.3%	Name drop frequency	100Gemini 3.1 Flash Lite (Preview) 100Gemini 3.1 Flash Lite (Reasoning) 100DeepSeek V3.1	9Claude 3 Haiku 20LFM2 24B 24GPT-5.4 Nano
86.4%	Narrator intent-glossing	100GPT-5.4 (Reasoning, Low) 100Gemini 3.1 Pro (Preview) 100Grok 4.1 Fast	16GPT-5 Nano 22Arcee AI: Trinity Large (Preview) 27Claude Sonnet 4
100.0%	Overuse of "that" (subordinate clause padding)	100Grok 4.20 (Beta) 100Z.AI GLM 4.7 Flash 100Gemini 3 Flash (Preview)	76ByteDance Seed 2.0 Lite 79Llama 3.1 70B 80Gemini 2.5 Flash
100.0%	Paragraph length variance	100Gemini 3.5 Flash (Reasoning) 100Xiaomi MIMO v2.5 Pro 100Ministral 3B	44Inception Mercury 47Mistral Small 3.2 24B 52Hermes 3 405B
98.3%	Passive voice overuse	100Qwen 3.6 35B 100Gemini 3.1 Pro (Preview) 100Grok 4	90Claude Sonnet 4.6 90ByteDance Seed 1.6 92ByteDance Seed 2.0 Mini
97.9%	Past progressive (was/were + -ing) overuse	100MoonshotAI: Kimi K2.5 100GPT-5 Nano 100GPT-4.1	51Stealth: Healer Alpha 52Gemini 3 Flash (Preview) 53Gemini 3 Flash (Preview, Reasoning)
88.8%	Pronoun-first sentence starts	100GPT-5.5 (Reasoning) 100Hermes 3 405B 100Grok 4.1 Fast	5Inception Mercury 33Mistral NeMO 39Qwen 3.5 35B
97.9%	Purple prose (modifier overload)	100Ministral 3B 100Llama 3.1 70B 100Gemini 3 Pro (Preview)	88Gemini 3.5 Flash (Reasoning) 92Gemini 3.1 Pro (Preview) 92Inception Mercury
100.0%	Repeated phrase echo	100GPT-4o, Aug. 6th (temp=0) 100Z.AI GLM 5 100Grok 4.20 (Beta)	—
100.0%	Sentence length variance	100GPT-5.4 Nano 100Rocinante 12B 100DeepSeek-V2 Chat	76Inception Mercury 91Stealth: Aurora Alpha 93Llama 3.1 8B
51.9%	Sentence opener variety	98Grok 4.1 Fast 88GPT-4o, Aug. 6th (temp=1) 87Llama 3.1 Nemotron 70B	26Inception Mercury 32Mistral Small 3.2 24B 33Gemma 4 26B (Reasoning)
29.7%	Subject-first sentence starts	89Qwen3 235B A22B Instruct 2507 88Writer: Palmyra X5 88Z.AI GLM 5	0Inception Mercury 0Stealth: Aurora Alpha 0GPT-OSS 120B
28.4%	Subordinate conjunction sentence starts	94Rocinante 12B 88Z.AI GLM 4.7 Flash 73Gemini 3.5 Flash (Reasoning)	0LFM2 24B 0Mistral Small Creative 0Grok 4.1 Fast
83.8%	Technical jargon density	100o4 Mini High 100Gemini 3.1 Pro (Preview) 100GPT-4o, May 13th (temp=0)	6GPT-5 Nano 15ByteDance Seed 1.6 18ByteDance Seed 2.0 Lite
64.4%	Useless dialogue additions	100Qwen 3.5 35B 100Gemma 4 31B (Reasoning) 100GPT-5.4 (Reasoning, Low)	0Ministral 3 8B 0Arcee AI: Trinity Mini 0GPT-4.1 Nano

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)