Literary fiction: old friends reunite

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
Claude Opus 4	92%
GPT-5.4	91%
Writer: Palmyra X5	90%
Qwen3 235B A22B Instruct 2507	89%
Grok 4.20 (Beta)	88%
Claude Sonnet 4	88%
GPT-5.4 (Reasoning, Low)	88%
GPT-5.4 Mini	88%
Z.AI GLM 5	88%
Mistral Medium 3.1	87%
Qwen 3.5 397B A17B	87%
GPT-5.4 (Reasoning)	87%
Claude Opus 4.5	87%
GPT-5.4 Mini (Reasoning)	87%
Mistral Large	86%
Qwen 3 32B	86%
Mistral Large 3	86%
Claude Sonnet 4.5	86%
GPT-5.4 Mini (Reasoning, Low)	86%
Mistral Large 2	86%

	Score	Cost	Time
Grok 4.20 (Beta)	88%	$0.017	14.1s
Writer: Palmyra X5	90%	$0.014	23.9s
Qwen3 235B A22B Instruct 2507	89%	$0.0013	1.2m
Mistral Medium 3.1	87%	$0.0052	38.3s
Mistral Small 4 (Reasoning)	85%	$0.0025	29.1s
Mistral Large	86%	$0.018	33.2s
DeepSeek V3 (2025-03-24)	85%	$0.0018	38.5s
Qwen 3 32B	86%	$0.0019	1.7m
GPT-5.4 Mini	88%	$0.015	16.1s
Z.AI GLM 5	88%	$0.011	1.1m
Hermes 3 405B	85%	$0.0054	35.9s
MiniMax M2.7	86%	$0.0040	1.3m
ByteDance Seed 1.6 Flash	84%	$0.0014	27.7s
Mistral Small 4	84%	$0.0022	26.2s
GPT-5.4 Nano (Reasoning, Low)	84%	$0.0044	18.2s
Grok 4.1 Fast	85%	$0.0026	47.0s
GPT-5.4 Nano	84%	$0.0051	18.4s
GPT-5.4 Mini (Reasoning)	87%	$0.030	32.6s
GPT-5.4 Mini (Reasoning, Low)	86%	$0.015	15.7s
Mistral Large 2	86%	$0.018	32.8s

	Score	Consistency	Stability
Claude Opus 4	92%	96%	89%
Qwen3 235B A22B Instruct 2507	89%	96%	86%
Writer: Palmyra X5	90%	96%	86%
GPT-5.4	91%	94%	86%
GPT-5.4 (Reasoning, Low)	88%	97%	85%
GPT-5.4 Mini (Reasoning)	87%	97%	85%
Z.AI GLM 5	88%	97%	85%
GPT-5.4 (Reasoning)	87%	96%	84%
Qwen 3.5 397B A17B	87%	95%	84%
Claude Sonnet 4.6 (Reasoning)	85%	97%	83%
GPT-5.4 Mini	88%	96%	83%
o4 Mini	84%	99%	83%
MiniMax M2.7	86%	96%	83%
GPT-5.2	84%	98%	82%
WizardLM 2 8x22b	84%	97%	82%
MiniMax M2.5	85%	95%	82%
Grok 4.1 Fast	85%	96%	82%
Mistral Large 2	86%	96%	82%
GPT-5	86%	96%	82%
Qwen 3 32B	86%	94%	82%

	Score	Cost	Speed	Stability
Writer: Palmyra X5	90%	$0.014	23.9s	86%
Qwen3 235B A22B Instruct 2507	89%	$0.0013	1.2m	86%
GPT-5.4 Mini	88%	$0.015	16.1s	83%
Grok 4.20 (Beta)	88%	$0.017	14.1s	82%
Z.AI GLM 5	88%	$0.011	1.1m	85%
GPT-5.4	91%	$0.049	1.4m	86%
GPT-5.4 Mini (Reasoning)	87%	$0.030	32.6s	85%
Mistral Medium 3.1	87%	$0.0052	38.3s	81%
Mistral Small 4 (Reasoning)	85%	$0.0025	29.1s	82%
GPT-5.4 Mini (Reasoning, Low)	86%	$0.015	15.7s	81%
Mistral Large 2	86%	$0.018	32.8s	82%
Grok 4.1 Fast	85%	$0.0026	47.0s	82%
GPT-5.4 Nano	84%	$0.0051	18.4s	81%
DeepSeek V3 (2025-03-24)	85%	$0.0018	38.5s	81%
o4 Mini	84%	$0.014	25.2s	83%
MiniMax M2.7	86%	$0.0040	1.3m	83%
Mistral Large	86%	$0.018	33.2s	81%
GPT-5.4 Nano (Reasoning, Low)	84%	$0.0044	18.2s	80%
Claude Sonnet 4	88%	$0.043	51.6s	81%
GPT-5.4 Nano (Reasoning)	84%	$0.0059	25.8s	81%

Rank	Model	Avg. Cost	Avg. Time	Stability	# 1	# 2	# 3	# 4	# 5	Total
66	Claude Opus 4	$0.250	1.5m	89%	94	94	92	90	89	92%
6	GPT-5.4	$0.049	1.4m	86%	94	93	91	89	86	91%
1	Writer: Palmyra X5	$0.014	23.9s	86%	93	90	89	89	88	90%
2	Qwen3 235B A22B Instruct 2507	$0.0013	1.2m	86%	92	91	90	89	85	89%
4	Grok 4.20 (Beta)	$0.017	14.1s	82%	94	90	89	87	81	88%
19	Claude Sonnet 4	$0.043	51.6s	81%	93	89	86	86	86	88%
21	GPT-5.4 (Reasoning, Low)	$0.060	1.4m	85%	90	89	88	87	85	88%
3	GPT-5.4 Mini	$0.015	16.1s	83%	91	88	87	86	86	88%
5	Z.AI GLM 5	$0.011	1.1m	85%	90	89	87	87	85	88%
8	Mistral Medium 3.1	$0.0052	38.3s	81%	92	88	88	87	81	87%
43	Qwen 3.5 397B A17B	$0.012	3.7m	84%	89	89	88	84	84	87%
84	GPT-5.4 (Reasoning)	$0.119	3.4m	84%	89	89	88	85	84	87%
36	Claude Opus 4.5	$0.082	51.4s	81%	90	90	86	85	83	87%
7	GPT-5.4 Mini (Reasoning)	$0.030	32.6s	85%	88	87	87	87	84	87%
17	Mistral Large	$0.018	33.2s	81%	90	90	88	84	79	86%
22	Qwen 3 32B	$0.0019	1.7m	82%	90	87	87	86	81	86%
24	Mistral Large 3	$0.0051	40.8s	78%	94	86	85	84	82	86%
29	Claude Sonnet 4.5	$0.048	47.9s	80%	90	90	86	83	82	86%
10	GPT-5.4 Mini (Reasoning, Low)	$0.015	15.7s	81%	91	85	85	85	84	86%
11	Mistral Large 2	$0.018	32.8s	82%	89	86	86	86	82	86%
30	Claude Sonnet 4.6	$0.041	39.3s	79%	90	88	85	83	82	86%
55	GPT-5	$0.062	2.5m	82%	90	86	85	84	84	86%
16	MiniMax M2.7	$0.0040	1.3m	83%	87	87	86	86	82	86%
26	MiniMax M2.5	$0.0044	2.2m	82%	89	87	87	83	81	85%
9	Mistral Small 4 (Reasoning)	$0.0025	29.1s	82%	88	87	86	85	80	85%
12	Grok 4.1 Fast	$0.0026	47.0s	82%	88	85	85	85	82	85%
47	Claude Opus 4.6	$0.088	1.1m	81%	88	87	86	82	81	85%
14	DeepSeek V3 (2025-03-24)	$0.0018	38.5s	81%	87	87	85	85	80	85%
85	Claude Opus 4.6 (Reasoning)	$0.114	1.5m	78%	90	87	84	83	81	85%
75	MoonshotAI: Kimi K2.5	$0.024	4.3m	81%	87	87	85	84	80	85%
50	GPT-5.1	$0.055	2.1m	81%	88	86	84	83	83	85%
28	Hermes 3 405B	$0.0054	35.9s	77%	93	86	86	84	76	85%
72	Claude Sonnet 4.6 (Reasoning)	$0.118	2.0m	83%	86	86	85	84	83	85%
39	Claude 3.5 Sonnet	$0.064	41.3s	81%	88	85	85	83	81	84%
13	GPT-5.4 Nano	$0.0051	18.4s	81%	87	85	84	83	82	84%
44	GPT-5.2	$0.057	1.5m	82%	85	85	84	83	83	84%
18	GPT-5.4 Nano (Reasoning, Low)	$0.0044	18.2s	80%	87	86	84	82	81	84%
41	ByteDance Seed 2.0 Lite	$0.012	2.0m	80%	87	86	85	81	81	84%
34	Z.AI GLM 5 Turbo	$0.011	30.3s	76%	89	87	82	82	79	84%
38	Grok 4.20 (Beta, Reasoning)	$0.041	33.7s	78%	88	85	85	85	76	84%
20	GPT-5.4 Nano (Reasoning)	$0.0059	25.8s	81%	86	86	84	82	81	84%
15	o4 Mini	$0.014	25.2s	83%	84	84	84	83	83	84%
32	WizardLM 2 8x22b	$0.0039	2.1m	82%	85	85	84	82	82	84%
23	ByteDance Seed 1.6 Flash	$0.0014	27.7s	80%	87	85	84	83	79	84%
25	Claude Haiku 4.5	$0.017	27.9s	81%	86	84	84	84	80	84%
27	Mistral Small 4	$0.0022	26.2s	77%	90	85	84	81	77	84%
31	GPT-4.1	$0.017	54.4s	80%	86	85	84	83	79	83%
33	Qwen 3.5 9B	$0.0013	1.2m	79%	87	84	83	83	79	83%
107	Gemini 3.1 Pro (Preview)	$0.148	2.3m	81%	84	84	83	82	80	83%
52	Ministral 3 14B	$0.0012	16.5s	71%	91	87	79	78	77	83%
48	DeepSeek V3.2	$0.0021	1.7m	77%	86	85	82	82	77	82%
106	Qwen 3.5 27B	$0.051	4.1m	78%	86	84	82	81	79	82%
35	Qwen 3.5 Flash	$0.0029	52.9s	79%	85	83	83	79	78	82%
95	ByteDance Seed 2.0 Mini	$0.0041	4.0m	76%	86	83	81	80	79	82%
37	Z.AI GLM 4.6	$0.0050	30.4s	77%	86	83	81	80	78	82%
65	Aion 2.0	$0.0083	1.3m	75%	86	86	81	78	76	82%
51	Qwen 3.5 35B	$0.019	1.0m	77%	84	84	83	82	74	81%
40	Mistral Small Creative	$0.0009	9.0s	75%	87	83	81	79	76	81%
42	GPT-5 Mini	$0.010	1.0m	79%	83	82	82	81	78	81%
96	Qwen 3.5 122B	$0.078	2.8m	80%	83	82	82	80	79	81%
57	DeepSeek V3 (2024-12-26)	$0.0027	44.5s	74%	87	85	80	78	76	81%
49	Rocinante 12B	$0.0018	34.3s	74%	86	86	83	76	74	81%
67	o4 Mini High	$0.042	1.3m	78%	83	81	81	80	79	81%
53	ByteDance Seed 1.6	$0.0093	1.7m	79%	82	82	81	80	79	81%
54	Gemini 2.5 Flash (Reasoning)	$0.011	21.0s	74%	87	82	80	79	76	81%
60	Z.AI GLM 4.5	$0.0062	46.2s	75%	85	83	79	79	77	81%
56	Claude 3.5 Haiku	$0.0052	9.8s	73%	85	85	81	79	72	81%
64	DeepSeek-V2 Chat	$0.0027	50.8s	74%	87	81	79	78	77	80%
63	Z.AI GLM 4.7	$0.012	1.8m	79%	81	81	80	80	78	80%
76	Llama 3.1 8B	$0.0003	2.0m	75%	85	80	79	79	77	80%
68	Ministral 3 8B	$0.0010	11.5s	71%	88	84	82	77	68	80%
45	Stealth: Healer Alpha	$0.0000	28.2s	76%	84	81	80	77	77	80%
73	Claude 3 Haiku	$0.0030	13.7s	70%	90	78	78	77	77	80%
98	Grok 4	$0.060	1.8m	75%	84	80	79	78	78	80%
82	Arcee AI: Trinity Large (Preview)	$0.0000	47.2s	71%	87	85	79	75	72	80%
59	Qwen 3.5 Plus (2026-02-15)	$0.0070	28.0s	75%	83	83	79	79	76	80%
78	Z.AI GLM 4.7 Flash	$0.0018	1.8m	75%	84	81	80	79	75	80%
91	Claude 3.7 Sonnet	$0.056	55.9s	73%	86	82	81	75	74	80%
77	Gemini 2.5 Pro	$0.039	36.9s	75%	83	82	81	81	71	80%
46	Ministral 8B	$0.0006	11.8s	75%	82	81	80	79	73	79%
70	LFM2 24B	$0.0003	29.8s	72%	86	79	78	77	76	79%
61	Grok 4 Fast	$0.0022	25.7s	74%	83	81	80	77	73	79%
69	Gemma 3 27B	$0.0010	55.7s	75%	82	82	80	75	74	79%
58	Ministral 3B	$0.0002	5.4s	74%	83	79	79	77	75	79%
86	GPT-4o, May 13th (temp=1)	$0.043	15.5s	72%	82	81	77	76	75	78%
80	Gemini 2.5 Flash	$0.0046	9.1s	70%	82	82	76	75	75	78%
62	Qwen 2.5 72B	$0.0016	38.6s	76%	80	79	78	78	75	78%
109	Hermes 3 70B	$0.0017	2.3m	68%	86	84	80	72	67	78%
93	Gemini 3 Pro (Preview)	$0.062	58.2s	75%	80	79	78	77	75	78%
81	Gemma 3 12B	$0.0004	40.3s	73%	81	80	77	76	74	78%
74	Stealth: Hunter Alpha	$0.0000	48.2s	74%	81	79	77	76	75	78%
71	Gemini 3 Flash (Preview, Reasoning)	$0.012	29.5s	75%	80	79	77	76	76	78%
79	GPT-4.1 Mini	$0.0026	16.2s	72%	82	79	76	75	75	77%
94	Ministral 3 3B	$0.0019	58.4s	70%	84	79	76	75	71	77%
87	GPT-4o, May 13th (temp=0)	$0.039	10.4s	73%	81	79	78	76	72	77%
89	GPT-4o, Aug. 6th (temp=1)	$0.021	23.6s	72%	80	80	77	76	71	77%
97	DeepSeek V3.1	$0.0023	1.9m	73%	80	79	78	75	72	77%
90	Mistral NeMO	$0.0009	9.6s	69%	81	81	75	74	70	76%
88	Nemotron 3 Super	$0.0000	43.1s	72%	81	78	77	73	71	76%
108	Cohere Command R+ (Aug. 2024)	$0.023	46.6s	69%	82	75	74	74	73	76%
83	Arcee AI: Trinity Mini	$0.0004	9.5s	72%	78	78	76	74	71	76%
112	GPT-4o, Aug. 6th (temp=0)	$0.050	34.3s	68%	80	77	73	72	71	75%
105	Llama 3.1 70B	$0.0025	35.8s	69%	81	76	76	71	68	75%
101	Gemini 3 Flash (Preview)	$0.0084	17.9s	69%	79	76	74	73	70	75%
111	Llama 3.1 Nemotron 70B	$0.0065	35.8s	66%	81	77	73	72	67	74%
102	Gemini 2.5 Flash Lite (Reasoning)	$0.0031	33.0s	70%	76	76	75	73	68	74%
100	Gemini 3.1 Flash Lite (Preview)	$0.0037	8.9s	69%	78	74	73	72	72	74%
99	Gemini 2.5 Flash Lite	$0.0011	11.3s	70%	77	76	74	70	70	73%
104	Inception Mercury 2	$0.0031	6.3s	69%	77	76	75	72	66	73%
92	Stealth: Aurora Alpha	$0.0000	9.4s	72%	75	74	74	72	71	73%
103	GPT-4o Mini (temp=0)	$0.0015	46.9s	72%	74	73	73	72	72	73%
114	GPT-4o Mini (temp=1)	$0.0016	42.6s	63%	81	76	70	69	67	73%
118	Mistral Small 3.2 24B	$0.010	7.0m	66%	78	75	74	73	62	72%
110	GPT-4.1 Nano	$0.0008	16.6s	67%	77	73	71	70	69	72%
115	GPT-5 Nano	$0.0042	1.5m	65%	77	71	70	69	67	71%
113	Gemma 3 4B	$0.0003	22.0s	64%	78	73	71	69	64	71%
116	Nemotron 3 Nano	$0.0013	1.8m	64%	78	76	72	65	64	71%
117	Inception Mercury	$0.022	33.5s	62%	74	73	67	67	64	69%
81.04%

Median	Evaluator	Top 3	Flop 3
100.0%	"Not X but Y" pattern overuse	100Mistral Small Creative 100ByteDance Seed 2.0 Mini 100GPT-4.1	0GPT-5 Nano 61Stealth: Hunter Alpha 76GPT-5.4 (Reasoning, Low)
48.1%	Adverb-first sentence starts	100Qwen3 235B A22B Instruct 2507 100Mistral Large 100Writer: Palmyra X5	0Inception Mercury 0Inception Mercury 2 0Stealth: Aurora Alpha
99.3%	Adverbs in dialogue tags	100Qwen 3.5 35B 100GPT-5.4 (Reasoning, Low) 100Mistral Small 3.2 24B	13GPT-4.1 Nano 43Claude Haiku 4.5 55Llama 3.1 Nemotron 70B
88.7%	AI-ism adverb frequency	100Grok 4.1 Fast 99ByteDance Seed 2.0 Lite 98Claude Opus 4.6	63GPT-4.1 Nano 66Z.AI GLM 4.5 66Gemma 3 4B
100.0%	AI-ism character names	100Gemini 2.5 Flash Lite 100Llama 3.1 8B 100Llama 3.1 70B	76Claude Opus 4 80Claude Opus 4.5 84Claude 3.5 Sonnet
100.0%	AI-ism location names	100Mistral Large 100GPT-5.4 Nano (Reasoning) 100Gemini 3 Flash (Preview)	96Rocinante 12B
50.6%	AI-ism word frequency	86GPT-5 84ByteDance Seed 2.0 Lite 84ByteDance Seed 1.6 Flash	0Stealth: Aurora Alpha 0Llama 3.1 Nemotron 70B 0GPT-4o, May 13th (temp=0)
93.3%	Cliché density	100Mistral Large 100GPT-4o, Aug. 6th (temp=1) 100Grok 4.20 (Beta, Reasoning)	13GPT-4o Mini (temp=0) 13Inception Mercury 33Inception Mercury 2
99.7%	Dialogue tag variety (said vs. fancy)	100Claude Sonnet 4.6 (Reasoning) 100Inception Mercury 100MiniMax M2.7	9Hermes 3 70B 18Stealth: Aurora Alpha 19GPT-4o Mini (temp=1)
88.7%	Em-dash & semicolon overuse	100Claude Opus 4.5 100Qwen 3.5 9B 100Z.AI GLM 4.7	0GPT-4o, Aug. 6th (temp=1) 0ByteDance Seed 1.6 0GPT-5 Nano
100.0%	Emotion telling (show vs. tell)	100Qwen 3.5 Plus (2026-02-15) 100ByteDance Seed 2.0 Lite 100Ministral 8B	76Mistral Small 3.2 24B 85Llama 3.1 70B 91GPT-4o, Aug. 6th (temp=0)
100.0%	Filter word density	100Gemma 3 12B 100ByteDance Seed 2.0 Lite 100MiniMax M2.7	64Llama 3.1 8B 64Nemotron 3 Nano 67Llama 3.1 70B
100.0%	Gibberish response detection	100Mistral Small 4 100Claude Opus 4.6 100Qwen 3.5 35B	23Llama 3.1 8B 80Qwen 3.5 9B 80Nemotron 3 Nano
100.0%	Markdown formatting overuse	100Qwen 2.5 72B 100Claude Sonnet 4.6 (Reasoning) 100Z.AI GLM 4.5	80Qwen 3.5 35B 80Ministral 3 8B 80Ministral 3B
100.0%	Missing dialogue indicators (quotation marks)	100Z.AI GLM 4.5 100Qwen 3.5 Plus (2026-02-15) 100GPT-4.1 Nano	60GPT-5 78Qwen 3.5 Flash 80Nemotron 3 Super
47.6%	Name drop frequency	100Gemma 3 12B 97GPT-4.1 Nano 97GPT-5 Nano	0Qwen 3.5 35B 0GPT-5.2 0GPT-5.4 (Reasoning)
85.4%	Narrator intent-glossing	100Z.AI GLM 4.5 100MiniMax M2.7 100Mistral Medium 3.1	0GPT-5 Nano 26Llama 3.1 Nemotron 70B 31Gemini 2.5 Flash Lite
100.0%	Overuse of "that" (subordinate clause padding)	100Ministral 8B 100Cohere Command R+ (Aug. 2024) 100Z.AI GLM 4.5	86ByteDance Seed 1.6 86Rocinante 12B 88Claude Haiku 4.5
100.0%	Paragraph length variance	100Z.AI GLM 5 100Ministral 3 8B 100Qwen 3.5 35B	42Inception Mercury 58Mistral Small 3.2 24B 73GPT-5 Nano
99.1%	Passive voice overuse	100GPT-5.4 Mini (Reasoning, Low) 100o4 Mini 100Qwen 3.5 397B A17B	84Llama 3.1 70B 89Rocinante 12B 92Claude Sonnet 4.6
100.0%	Past progressive (was/were + -ing) overuse	100GPT-5 Mini 100Stealth: Aurora Alpha 100GPT-4o Mini (temp=1)	44Z.AI GLM 4.7 Flash 49Z.AI GLM 4.7 49Rocinante 12B
73.1%	Pronoun-first sentence starts	100GPT-5.2 100GPT-5.4 Mini (Reasoning, Low) 100GPT-5.4 (Reasoning)	0Gemma 3 4B 1GPT-4.1 Nano 1Z.AI GLM 4.7
97.4%	Purple prose (modifier overload)	100ByteDance Seed 1.6 Flash 100Nemotron 3 Nano 100Stealth: Aurora Alpha	74Mistral Small 3.2 24B 77Gemma 3 4B 80Gemma 3 27B
100.0%	Repeated phrase echo	100Qwen 3.5 9B 100Claude Sonnet 4.6 100DeepSeek V3.2	—
100.0%	Sentence length variance	100DeepSeek V3 (2024-12-26) 100o4 Mini High 100Claude Sonnet 4.6	84Mistral Small 3.2 24B 89Inception Mercury 98GPT-4o, Aug. 6th (temp=0)
57.4%	Sentence opener variety	96Claude 3.5 Haiku 95Grok 4.1 Fast 94GPT-4o, Aug. 6th (temp=1)	35Qwen 3.5 35B 36Qwen 3.5 Flash 37GPT-5 Nano
16.8%	Subject-first sentence starts	96Writer: Palmyra X5 90Qwen3 235B A22B Instruct 2507 84Llama 3.1 8B	0Z.AI GLM 4.7 0Inception Mercury 2 0DeepSeek V3.1
30.5%	Subordinate conjunction sentence starts	73Llama 3.1 8B 72GPT-4.1 Nano 71Claude Haiku 4.5	0MiniMax M2.5 0Z.AI GLM 4.7 Flash 0Gemini 3 Flash (Preview)
81.1%	Technical jargon density	100Qwen 3.5 35B 100Mistral Small 3.2 24B 100Hermes 3 405B	8GPT-5 Nano 30Gemma 3 4B 30GPT-4o Mini (temp=1)
58.4%	Useless dialogue additions	100Gemini 3.1 Pro (Preview) 100Qwen 3.5 27B 100Qwen 3.5 35B	0Gemini 2.5 Flash Lite (Reasoning) 0GPT-4o Mini (temp=0) 0Stealth: Aurora Alpha

Bad Writing Habits

Literary fiction: old friends reunite

Performance Score Distribution (Top 20)

Price-Performance Score Distribution (Top 20)

Most Stable Models (Top 20)

Top Overall Models (Top 20)