Fantasy: entering an ancient ruin

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	92%
GPT-5.6 Sol (Reasoning)	91%
GPT-5.6 Terra	90%
GPT-5.5 (Reasoning, Low)	90%
GPT-5.4 (Reasoning)	89%
GPT-5.6 Terra (Reasoning)	89%
GPT-5.5 (Reasoning)	89%
GPT-5.6 Luna (Reasoning)	89%
GPT-5.6 Luna	89%
GPT-5.5	87%
Claude Opus 5	87%
GPT-5.4 (Reasoning, Low)	86%
Claude Opus 5 (Reasoning, Low)	86%
Claude Opus 5 (Reasoning)	85%
GPT-5.4 Mini (Reasoning)	84%
GPT-5.4	84%
GPT-5.4 Mini	83%
MoonshotAI: Kimi K3 (Reasoning, Low)	83%
Qwen3.6 Max Preview	83%
GPT-5.4 Mini (Reasoning, Low)	83%

	Score	Cost	Time
GPT-5.6 Luna	89%	$0.016	17.1s
GPT-5.6 Luna (Reasoning)	89%	$0.018	20.1s
Gemini 3.5 Flash Lite (Reasoning, Minimal)	80%	$0.0042	7.9s
GPT-5.4 Mini (Reasoning, Low)	83%	$0.016	18.6s
GPT-5.4 Mini	83%	$0.016	18.8s
GPT-5.6 Terra	90%	$0.054	43.5s
GPT-5.6 Terra (Reasoning)	89%	$0.045	45.0s
GPT-5.4 Mini (Reasoning)	84%	$0.024	29.9s
Qwen 3.6 Flash	81%	$0.0087	35.9s
ByteDance Seed 1.6 Flash	76%	$0.0014	29.6s
Qwen 3.6 35B	78%	$0.0064	51.6s
Mistral Small 4	76%	$0.0015	19.7s
Muse Spark 1.1 (Reasoning, Minimal)	80%	$0.013	22.9s
Muse Spark 1.1 (Reasoning, Medium)	81%	$0.015	24.6s
Qwen 3.5 9B	79%	$0.0008	56.9s
GPT-5.4 Nano	77%	$0.0050	17.8s
Qwen3 235B A22B Instruct 2507	78%	$0.0010	56.7s
MoonshotAI: Kimi K3 (Reasoning, Low)	83%	$0.027	1.1m
Grok 4.20	80%	$0.0097	52.7s
DeepSeek V4 Flash (Reasoning)	76%	$0.0007	36.4s

	Score	Cost	Speed	Stability
GPT-5.6 Luna	89%	$0.016	17.1s	87%
GPT-5.6 Luna (Reasoning)	89%	$0.018	20.1s	86%
GPT-5.6 Terra	90%	$0.054	43.5s	89%
GPT-5.6 Terra (Reasoning)	89%	$0.045	45.0s	84%
GPT-5.4 Mini	83%	$0.016	18.8s	80%
GPT-5.4 Mini (Reasoning, Low)	83%	$0.016	18.6s	80%
GPT-5.6 Sol	92%	$0.103	1.2m	88%
GPT-5.6 Sol (Reasoning)	91%	$0.107	1.2m	88%
GPT-5.4 (Reasoning, Low)	86%	$0.056	1.4m	85%
GPT-5.4 Mini (Reasoning)	84%	$0.024	29.9s	76%
Claude Opus 5	87%	$0.080	54.5s	84%
MoonshotAI: Kimi K3 (Reasoning, Low)	83%	$0.027	1.1m	79%
GPT-5.4 (Reasoning)	89%	$0.079	2.2m	85%
Gemini 3.5 Flash Lite (Reasoning, Minimal)	80%	$0.0042	7.9s	74%
Muse Spark 1.1 (Reasoning, Medium)	81%	$0.015	24.6s	75%
GPT-5.4	84%	$0.048	1.4m	81%
Qwen 3.6 Flash	81%	$0.0087	35.9s	74%
Grok 4.20	80%	$0.0097	52.7s	76%
Qwen 3.5 9B	79%	$0.0008	56.9s	75%
GPT-5.4 Nano	77%	$0.0050	17.8s	75%

Rank	Model	Avg. Cost	Avg. Time	Stability	# 1	# 2	# 3	# 4	# 5	Total
7	GPT-5.6 Sol	$0.103	1.2m	88%	95	92	91	90	89	92%
8	GPT-5.6 Sol (Reasoning)	$0.107	1.2m	88%	92	91	90	90	89	91%
3	GPT-5.6 Terra	$0.054	43.5s	89%	91	91	90	90	90	90%
32	GPT-5.5 (Reasoning, Low)	$0.148	1.9m	87%	93	92	92	88	87	90%
13	GPT-5.4 (Reasoning)	$0.079	2.2m	85%	93	89	89	89	86	89%
4	GPT-5.6 Terra (Reasoning)	$0.045	45.0s	84%	93	92	91	86	84	89%
49	GPT-5.5 (Reasoning)	$0.152	1.9m	86%	91	91	90	88	85	89%
2	GPT-5.6 Luna (Reasoning)	$0.018	20.1s	86%	91	90	88	88	87	89%
1	GPT-5.6 Luna	$0.016	17.1s	87%	90	89	89	88	87	89%
86	GPT-5.5	$0.168	1.8m	84%	89	88	86	86	86	87%
11	Claude Opus 5	$0.080	54.5s	84%	89	89	88	86	83	87%
9	GPT-5.4 (Reasoning, Low)	$0.056	1.4m	85%	88	87	86	85	85	86%
43	Claude Opus 5 (Reasoning, Low)	$0.106	1.1m	80%	90	87	85	84	82	86%
25	Claude Opus 5 (Reasoning)	$0.095	1.0m	83%	87	85	85	85	84	85%
10	GPT-5.4 Mini (Reasoning)	$0.024	29.9s	76%	91	87	83	81	80	84%
16	GPT-5.4	$0.048	1.4m	81%	87	86	84	82	81	84%
5	GPT-5.4 Mini	$0.016	18.8s	80%	86	85	83	83	80	83%
12	MoonshotAI: Kimi K3 (Reasoning, Low)	$0.027	1.1m	79%	86	85	84	83	78	83%
90	Qwen3.6 Max Preview	$0.060	4.4m	80%	85	84	83	82	81	83%
6	GPT-5.4 Mini (Reasoning, Low)	$0.016	18.6s	80%	85	84	83	82	80	83%
51	Qwen3.7 Max	$0.056	1.9m	77%	88	84	82	81	79	83%
24	Grok 4.5 (Reasoning, High)	$0.026	1.4m	77%	86	85	82	79	79	82%
15	Muse Spark 1.1 (Reasoning, Medium)	$0.015	24.6s	75%	86	85	80	80	77	81%
17	Qwen 3.6 Flash	$0.0087	35.9s	74%	86	84	80	79	74	81%
62	Claude Opus 4.7 (Reasoning)	$0.080	36.0s	76%	83	83	80	80	76	80%
57	Claude Opus 4.8 (Reasoning)	$0.070	44.6s	76%	84	82	80	79	77	80%
72	Qwen 3.5 397B A17B	$0.031	2.7m	74%	85	83	81	80	73	80%
23	Muse Spark 1.1 (Reasoning, Minimal)	$0.013	22.9s	72%	87	85	80	75	75	80%
39	Grok 4.20 (Reasoning)	$0.017	1.4m	72%	86	83	79	78	74	80%
28	Hermes 3 405B	$0.0030	1.6m	73%	85	85	80	78	73	80%
110	Gemini 3.1 Pro (Preview)	$0.079	1.6m	73%	87	81	78	78	76	80%
67	GPT-5.1	$0.057	1.4m	74%	83	83	79	78	76	80%
84	Claude Opus 4.8 (Reasoning, Low)	$0.071	44.7s	72%	87	83	79	76	75	80%
14	Gemini 3.5 Flash Lite (Reasoning, Minimal)	$0.0042	7.9s	74%	86	83	81	76	73	80%
18	Grok 4.20	$0.0097	52.7s	76%	83	81	80	78	76	80%
44	Claude Sonnet 4.6	$0.034	47.3s	73%	84	80	77	77	77	79%
58	Claude Opus 4.7	$0.062	28.5s	75%	84	79	79	77	76	79%
19	Qwen 3.5 9B	$0.0008	56.9s	75%	81	81	79	79	75	79%
41	GPT-4.1	$0.018	45.5s	71%	86	77	77	77	76	79%
129	GPT-5	$0.068	2.6m	73%	83	81	78	76	76	79%
29	Z.AI GLM 5	$0.0078	45.3s	72%	83	82	78	78	72	79%
99	Aion 3.0 Mini	$0.0051	1.1m	62%	96	77	75	75	70	78%
26	Qwen 3.6 35B	$0.0064	51.6s	73%	82	81	81	80	69	78%
22	Qwen3 235B A22B Instruct 2507	$0.0010	56.7s	75%	82	79	78	77	75	78%
48	Qwen 3.5 Plus (2026-04-20)	$0.016	1.6m	74%	81	81	81	78	71	78%
47	Grok 4.5 (Reasoning, Low)	$0.018	59.8s	72%	85	81	81	75	70	78%
108	Claude Opus 4.6 (Reasoning)	$0.081	1.2m	74%	82	80	78	76	74	78%
46	Mistral Large 2	$0.013	31.1s	70%	83	81	76	75	74	78%
77	MoonshotAI: Kimi K3 (Reasoning, High)	$0.034	1.8m	73%	82	79	77	75	74	78%
142	MoonshotAI: Kimi K2.6	$0.043	3.8m	71%	84	77	76	76	74	77%
31	GPT-5 Mini	$0.010	41.6s	73%	80	78	76	76	75	77%
56	Z.AI GLM 5 Turbo	$0.0074	34.2s	69%	84	81	76	75	69	77%
69	Claude Sonnet 4.5	$0.032	37.0s	70%	83	81	79	75	68	77%
55	Claude Sonnet 5 (Reasoning)	$0.025	33.1s	72%	81	80	76	76	72	77%
20	GPT-5.4 Nano	$0.0050	17.8s	75%	79	78	78	76	74	77%
53	GPT-4o Mini (temp=1)	$0.0012	28.4s	68%	83	82	76	76	67	77%
60	Z.AI GLM 5.1	$0.013	1.8m	74%	78	78	77	76	74	77%
133	Claude Opus 4.6	$0.075	1.2m	70%	82	80	77	74	70	77%
98	GPT-5.2	$0.058	1.5m	74%	79	78	77	76	74	77%
30	o4 Mini	$0.015	23.0s	74%	79	79	78	75	73	77%
80	Claude Sonnet 4.6 (Reasoning)	$0.047	1.1m	73%	80	78	77	74	74	76%
38	DeepSeek V4 Flash (Reasoning)	$0.0007	36.4s	71%	83	78	77	72	72	76%
88	Grok 4.3 (Reasoning)	$0.017	1.9m	70%	82	81	79	73	67	76%
120	ByteDance Seed 1.6	$0.013	2.6m	68%	84	78	74	73	73	76%
21	DeepSeek V4 Flash	$0.0007	28.1s	75%	78	76	76	76	75	76%
65	Gemini 2.5 Pro	$0.038	38.4s	73%	80	77	76	76	73	76%
34	ByteDance Seed 1.6 Flash	$0.0014	29.6s	72%	80	80	79	72	69	76%
37	Mistral Small 4	$0.0015	19.7s	71%	81	79	78	76	67	76%
33	DeepSeek-V2 Chat	$0.0023	46.2s	73%	79	76	76	75	75	76%
36	DeepSeek V4 Pro	$0.0042	1.2m	75%	77	76	76	76	75	76%
93	Qwen 3.5 35B	$0.0083	34.6s	64%	83	83	72	71	71	76%
156	Thinking Machines Inkling (Reasoning)	$0.025	6.9m	72%	79	77	77	76	70	76%
94	DeepSeek V4 Pro (Reasoning)	$0.0037	1.8m	68%	82	80	75	73	70	76%
27	Gemini 3.1 Flash Lite (Preview)	$0.0029	8.8s	72%	80	77	76	73	73	76%
128	Qwen 3.6 27B	$0.021	2.2m	67%	81	80	73	73	72	76%
95	ByteDance Seed 2.0 Lite	$0.012	2.2m	71%	80	79	78	73	67	76%
40	Gemini 3.1 Flash Lite (Reasoning)	$0.0027	8.7s	70%	81	77	75	72	71	75%
50	Gemini 3.6 Flash (Reasoning, Minimal)	$0.015	12.9s	71%	80	77	76	74	70	75%
59	Writer: Palmyra X5	$0.012	23.7s	70%	80	79	76	73	68	75%
52	Gemini 3.5 Flash Lite (Reasoning)	$0.0040	7.4s	69%	81	77	75	73	69	75%
66	Xiaomi MIMO v2.5	$0.0069	38.4s	69%	82	75	74	73	73	75%
42	GPT-5.4 Nano (Reasoning)	$0.0059	21.4s	72%	79	75	75	73	73	75%
97	MiniMax M2.5	$0.0033	1.3m	66%	84	75	73	71	71	75%
61	DeepSeek V3 (2025-03-24)	$0.0015	30.6s	69%	81	77	74	72	72	75%
35	Gemini 3.1 Flash Lite	$0.0026	7.9s	72%	77	76	74	74	73	75%
116	Claude Sonnet 5 (Reasoning, Low)	$0.025	32.4s	64%	83	80	73	73	66	75%
96	Claude Sonnet 5	$0.026	34.8s	67%	83	78	76	70	67	75%
68	Gemini 3.5 Flash (Reasoning, Minimal)	$0.017	11.3s	68%	82	77	75	71	69	75%
109	MiniMax M3	$0.0045	2.7m	71%	78	76	74	73	72	75%
134	MoonshotAI: Kimi K2.5	$0.018	2.8m	69%	78	78	75	74	68	75%
74	Thinking Machines Inkling	$0.0097	1.0m	70%	79	78	76	70	70	75%
54	Mistral Medium 3.1	$0.0048	33.3s	71%	76	76	76	75	68	74%
45	GPT-5.4 Nano (Reasoning, Low)	$0.0056	19.7s	72%	77	75	74	73	72	74%
100	Qwen 3 32B	$0.0015	56.9s	65%	83	78	73	69	68	74%
79	Aion 3.0	$0.021	55.8s	71%	78	75	74	73	71	74%
78	Z.AI GLM 5.2 (Reasoning, High)	$0.012	59.5s	70%	80	76	75	70	70	74%
160	Claude Opus 4	$0.195	1.4m	69%	78	77	73	73	69	74%
70	Grok 4.3	$0.0070	44.9s	70%	78	74	73	73	72	74%
102	o4 Mini High	$0.035	59.1s	71%	78	75	75	72	69	74%
130	Gemini 3.6 Flash (Reasoning)	$0.036	28.9s	65%	80	79	72	70	67	74%
101	Gemini 3.5 Flash (Reasoning)	$0.042	25.0s	70%	77	76	75	73	67	74%
63	Claude Haiku 4.5	$0.011	21.1s	70%	77	75	75	73	68	74%
106	DeepSeek V3.2	$0.0014	1.6m	67%	78	76	71	71	71	73%
73	Qwen 3.5 122B	$0.011	29.7s	70%	78	76	75	69	69	73%
64	Ministral 3 14B	$0.0007	18.0s	68%	79	74	73	73	68	73%
122	Mistral Large 3	$0.0033	32.5s	62%	86	74	71	69	66	73%
118	Xiaomi MIMO v2.5 Pro	$0.0091	58.9s	65%	81	76	71	70	69	73%
121	Hermes 3 70B	$0.0011	1.5m	65%	81	73	72	71	68	73%
83	Mistral NeMO	$0.0005	7.9s	65%	80	79	74	67	65	73%
81	Gemma 3 12B	$0.0003	51.8s	68%	79	73	73	72	68	73%
76	GPT-4o Mini (temp=0)	$0.0011	28.9s	68%	77	76	72	70	69	73%
82	Mistral Small 4 (Reasoning)	$0.0026	37.5s	68%	78	73	72	71	70	73%
112	Qwen 3.5 Flash	$0.0021	46.0s	64%	81	74	71	70	69	73%
71	Gemini 2.5 Flash Lite	$0.0010	11.1s	68%	78	75	73	70	68	73%
85	GPT-4o, Aug. 6th (temp=1)	$0.017	16.5s	68%	77	75	73	69	69	73%
91	Gemini 2.5 Flash	$0.0061	12.2s	66%	79	73	71	70	70	73%
119	Cohere Command R+ (Aug. 2024)	$0.021	51.5s	67%	79	73	72	70	68	72%
89	Qwen 3.5 Plus (2026-02-15)	$0.0059	34.2s	67%	77	75	71	70	70	72%
153	Claude Opus 4.5	$0.067	53.7s	61%	83	75	70	68	66	72%
150	ByteDance Seed 2.0 Mini	$0.0048	5.3m	70%	74	74	73	70	68	72%
75	Laguna XS 2.1	$0.0003	16.8s	68%	76	73	71	70	70	72%
87	Ministral 8B	$0.0004	11.7s	66%	78	75	71	70	66	72%
92	Z.AI GLM 4.7 Flash	$0.0016	1.2m	69%	73	73	71	71	70	72%
111	Gemma 3 27B	$0.0005	48.8s	65%	79	71	71	71	67	72%
104	Aion 2.0	$0.0064	1.5m	70%	73	72	72	71	70	72%
117	Qwen 3.5 27B	$0.011	1.0m	67%	76	74	73	68	65	71%
113	GPT-4.1 Mini	$0.0031	19.2s	64%	78	72	71	68	66	71%
137	Z.AI GLM 4.6	$0.0063	1.1m	64%	78	73	70	68	65	71%
115	Qwen 2.5 72B	$0.0010	39.4s	66%	74	73	70	70	64	70%
132	DeepSeek V3 (2024-12-26)	$0.0022	45.8s	63%	77	72	69	68	64	70%
105	Ministral 3 8B	$0.0008	19.6s	66%	74	72	69	69	67	70%
103	Gemini 3 Flash (Preview, Reasoning)	$0.011	25.8s	69%	71	71	70	69	68	70%
135	MiniMax M2.7	$0.0041	1.0m	64%	76	74	72	65	61	70%
131	Gemma 3 4B	$0.0002	16.6s	62%	78	69	67	67	67	70%
126	Gemini 2.5 Flash (Reasoning)	$0.0099	20.4s	65%	75	71	68	68	66	70%
139	DeepSeek V3.1	$0.0022	1.4m	63%	77	73	71	66	61	70%
114	Gemini 3 Flash (Preview)	$0.0065	16.3s	66%	72	72	69	68	66	70%
144	Claude Sonnet 4	$0.030	43.6s	63%	74	74	68	67	64	69%
136	Cydonia 24B V4.1	$0.0014	47.4s	63%	76	71	69	67	64	69%
124	Z.AI GLM 4.5	$0.0061	49.7s	67%	72	69	69	68	68	69%
125	Laguna S 2.1	$0.0004	13.5s	64%	75	71	71	66	61	69%
151	Gemma 4 31B (Reasoning)	$0.0012	2.3m	60%	78	71	67	64	64	69%
123	Z.AI GLM 4.5 Air	$0.0026	49.0s	67%	71	70	69	67	66	69%
107	Ministral 3B	$0.0001	3.5s	66%	71	70	69	67	66	68%
143	Z.AI GLM 4.7	$0.0085	1.1m	63%	74	72	68	65	63	68%
127	Ministral 3 3B	$0.0005	12.1s	64%	73	69	68	65	65	68%
138	Gemma 4 31B	$0.0008	1.2m	65%	70	69	67	67	66	68%
149	GPT-4o, Aug. 6th (temp=0)	$0.017	17.4s	57%	77	71	64	63	63	68%
145	WizardLM 2 8x22b	$0.0021	23.8s	60%	72	70	66	62	60	66%
161	Mistral Small 3.2 24B	$0.012	8.0m	61%	72	68	66	65	60	66%
148	Gemma 4 26B	$0.0008	1.1m	59%	72	69	64	62	62	66%
140	GPT-4.1 Nano	$0.0007	12.3s	62%	70	67	66	65	61	66%
141	Arcee AI: Trinity Mini	$0.0003	10.1s	63%	68	66	65	64	62	65%
154	Gemma 4 26B (Reasoning)	$0.0011	1.3m	59%	72	66	65	61	61	65%
146	Gemini 2.5 Flash Lite (Reasoning)	$0.0030	27.6s	61%	69	67	66	62	60	65%
147	Llama 3.1 70B	$0.0010	37.9s	59%	71	66	65	63	58	65%
158	GPT-5 Nano	$0.0042	1.4m	58%	71	65	63	63	59	64%
159	GPT-OSS 120B	$0.0014	3.9m	60%	66	65	63	63	60	63%
157	Nemotron 3 Super	$0.0000	1.2m	59%	66	66	62	62	57	63%
155	Nemotron 3 Nano	$0.0009	1.1m	60%	63	63	62	61	59	62%
152	Inception Mercury 2	$0.0030	7.5s	59%	65	63	63	61	56	62%
75.47%

Median	Evaluator	Top 3	Flop 3
68.5%	"Not X but Y" pattern overuse	100Gemma 3 12B 100Hermes 3 405B 100Hermes 3 70B	0Z.AI GLM 5.2 (Reasoning, High) 0Writer: Palmyra X5 0GPT-5 Nano
56.4%	Adverb-first sentence starts	100GPT-5.4 Mini 100Grok 4.5 (Reasoning, High) 100GPT-5.4 (Reasoning)	0Inception Mercury 2 0Arcee AI: Trinity Mini 7Qwen 3.5 27B
97.8%	Adverbs in dialogue tags	100DeepSeek V4 Pro 100Gemma 4 31B 100GPT-5.6 Terra	40Claude Sonnet 4.6 (Reasoning) 49Claude Opus 4.7 51Gemini 3.6 Flash (Reasoning)
85.5%	AI-ism adverb frequency	100ByteDance Seed 1.6 97o4 Mini High 97GPT-5 Mini	55GPT-4.1 Nano 66GPT-4o Mini (temp=0) 68Claude Opus 4.7
100.0%	AI-ism character names	100ByteDance Seed 1.6 100Aion 3.0 Mini 100Ministral 3 3B	92GPT-4.1 96Claude Opus 5 (Reasoning) 96Grok 4.3
100.0%	AI-ism location names	100Ministral 3B 100DeepSeek V4 Pro 100Qwen 3.6 Flash	—
33.9%	AI-ism word frequency	80Claude Opus 5 (Reasoning) 79Claude Opus 5 (Reasoning, Low) 77Claude Opus 4.7 (Reasoning)	0GPT-4.1 Nano 0Gemini 2.5 Flash Lite (Reasoning) 0Gemma 3 4B
100.0%	Cliché density	100GPT-4.1 100Z.AI GLM 5.1 100GPT-5.4 Nano	73Nemotron 3 Nano 73Inception Mercury 2 73GPT-4o, Aug. 6th (temp=0)
39.3%	Dialogue tag variety (said vs. fancy)	100Claude Opus 5 100Claude Sonnet 4.6 100Gemini 3.1 Flash Lite (Preview)	0GPT-OSS 120B 0Gemma 3 12B 0Nemotron 3 Super
0.8%	Em-dash & semicolon overuse	100Mistral Small 3.2 24B 100Qwen3.6 Max Preview 99Qwen 3.6 Flash	0Mistral Large 3 0Grok 4.3 (Reasoning) 0Gemma 4 26B
100.0%	Emotion telling (show vs. tell)	100Gemma 4 31B 100Mistral Large 2 100Claude Opus 4.8 (Reasoning)	36Llama 3.1 70B 65GPT-4o Mini (temp=0) 68GPT-4o, Aug. 6th (temp=0)
88.0%	Filter word density	100GPT-5.6 Terra (Reasoning) 100Claude Opus 5 (Reasoning) 100Writer: Palmyra X5	0Gemma 4 26B (Reasoning) 0Nemotron 3 Nano 0GPT-OSS 120B
100.0%	Gibberish response detection	100Claude Opus 4.7 (Reasoning) 100Gemini 2.5 Flash (Reasoning) 100MoonshotAI: Kimi K2.5	80Z.AI GLM 4.6 87Hermes 3 70B 91DeepSeek V3 (2025-03-24)
100.0%	Markdown formatting overuse	100GPT-4.1 Nano 100Gemma 4 31B 100WizardLM 2 8x22b	40Mistral Large 3 55Ministral 8B 60Ministral 3 8B
100.0%	Missing dialogue indicators (quotation marks)	100o4 Mini High 100GPT-5.1 100MoonshotAI: Kimi K2.6	0Gemini 3.1 Flash Lite (Reasoning) 0Gemini 3.1 Flash Lite 0Gemini 3.1 Flash Lite (Preview)
69.4%	Name drop frequency	99GPT-5 Mini 97Gemma 3 4B 97Z.AI GLM 4.6	10GPT-5.2 27Qwen3 235B A22B Instruct 2507 27Z.AI GLM 4.5 Air
41.0%	Narrator intent-glossing	100GPT-5.6 Sol 100GPT-5.6 Sol (Reasoning) 97Qwen3.6 Max Preview	0Nemotron 3 Nano 0Inception Mercury 2 0Nemotron 3 Super
100.0%	Overuse of "that" (subordinate clause padding)	100Grok 4.5 (Reasoning, High) 100Qwen3.6 Max Preview 100GPT-5 Mini	40Mistral Small 3.2 24B 61Llama 3.1 70B 66GPT-4o, Aug. 6th (temp=0)
99.6%	Paragraph length variance	100DeepSeek V3 (2024-12-26) 100Claude Sonnet 4.6 100MoonshotAI: Kimi K3 (Reasoning, Low)	11Mistral Small 3.2 24B 35WizardLM 2 8x22b 50GPT-4o, Aug. 6th (temp=1)
97.3%	Passive voice overuse	100DeepSeek V3 (2025-03-24) 100Grok 4.5 (Reasoning, Low) 100Qwen3 235B A22B Instruct 2507	83ByteDance Seed 2.0 Mini 83Llama 3.1 70B 85Claude Sonnet 5
97.0%	Past progressive (was/were + -ing) overuse	100ByteDance Seed 1.6 100Gemini 3.5 Flash (Reasoning, Minimal) 100GPT-5.4 (Reasoning, Low)	14Z.AI GLM 4.7 37Gemma 4 26B 38Gemma 4 26B (Reasoning)
97.7%	Pronoun-first sentence starts	100DeepSeek-V2 Chat 100Gemini 3.6 Flash (Reasoning) 100Qwen3 235B A22B Instruct 2507	30Mistral Small 3.2 24B 34Mistral NeMO 64Z.AI GLM 4.7 Flash
95.2%	Purple prose (modifier overload)	100Nemotron 3 Super 100Nemotron 3 Nano 100Mistral Small 3.2 24B	76Gemini 3.5 Flash (Reasoning) 78Gemini 3.6 Flash (Reasoning, Minimal) 79Gemini 3.1 Pro (Preview)
100.0%	Repeated phrase echo	100ByteDance Seed 1.6 100ByteDance Seed 1.6 Flash 100Gemma 3 27B	—
100.0%	Sentence length variance	100GPT-5.4 Mini (Reasoning) 100Claude Opus 4.6 (Reasoning) 100ByteDance Seed 1.6 Flash	57Mistral Small 3.2 24B 74WizardLM 2 8x22b 82Llama 3.1 70B
56.0%	Sentence opener variety	86Gemini 3.5 Flash Lite (Reasoning) 86Claude Sonnet 5 (Reasoning, Low) 85GPT-4o Mini (temp=1)	33GPT-5 Nano 34Mistral Small 3.2 24B 37Qwen 3.5 9B
46.5%	Subject-first sentence starts	93Claude Opus 5 90GPT-5.5 (Reasoning, Low) 89GPT-5.4 (Reasoning, Low)	2Arcee AI: Trinity Mini 3GPT-5 Nano 3Ministral 3 3B
44.0%	Subordinate conjunction sentence starts	100Gemini 3.1 Flash Lite (Preview) 100Gemini 3.1 Flash Lite 99Gemini 3.5 Flash Lite (Reasoning, Minimal)	0Inception Mercury 2 0Qwen 2.5 72B 0MiniMax M3
32.9%	Technical jargon density	100GPT-5.6 Sol 100GPT-5.6 Sol (Reasoning) 98GPT-5.6 Luna	0Gemma 4 31B (Reasoning) 0Z.AI GLM 5.1 0MiniMax M2.5
52.4%	Useless dialogue additions	100Claude Opus 4.6 (Reasoning) 100Gemini 3.1 Flash Lite 100GPT-5.4 (Reasoning)	0Gemma 3 27B 0Inception Mercury 2 0Arcee AI: Trinity Mini

Bad Writing Habits

Fantasy: entering an ancient ruin

Performance Score Distribution (Top 20)

Price-Performance Score Distribution (Top 20)

Most Stable Models (Top 20)

Top Overall Models (Top 20)