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.

0-shot Creative writingRule following

Performance Score Distribution (Top 20)

Click a model name to view its detail page.

Rank	Model	Avg. Cost	Avg. Time	Stability	# 1	# 2	# 3	# 4	# 5	Total
1	Claude 3.5 Haiku	$0.0021	8.5s	88%	99	96	95	91	90	94%
4	Qwen 3.5 397B A17B	$0.016	1.7m	87%	97	93	93	92	88	92%
32	Claude Opus 4.6	$0.074	1.2m	87%	95	91	91	90	88	91%
2	GPT-5 Mini	$0.0097	41.1s	87%	92	92	89	89	89	90%
52	GPT-5	$0.064	2.5m	85%	90	90	89	87	85	88%
45	MoonshotAI: Kimi K2.5	$0.021	3.1m	81%	93	91	86	86	85	88%
5	GPT-4.1	$0.017	35.0s	84%	91	90	89	86	85	88%
18	Mistral Large 2	$0.012	33.6s	77%	94	90	86	85	79	87%
48	Claude Opus 4.5	$0.067	53.3s	80%	92	89	85	85	84	87%
3	Gemini 3 Flash (Preview)	$0.0072	19.2s	83%	89	88	87	87	82	87%
9	Llama 3.1 70B	$0.0008	39.0s	78%	93	89	86	83	80	87%
31	Claude 3.5 Sonnet	$0.046	36.1s	81%	89	89	86	84	83	86%
54	GPT-5.2	$0.071	1.8m	84%	88	87	86	85	84	86%
17	Rocinante 12B	$0.0007	17.7s	74%	94	91	83	83	78	86%
39	Claude Sonnet 4.5	$0.034	43.0s	77%	90	90	85	84	78	85%
7	Mistral Large	$0.011	28.6s	82%	87	87	85	85	82	85%
36	Gemini 3 Pro (Preview)	$0.053	53.4s	84%	87	86	85	85	84	85%
47	GPT-5.1	$0.058	1.3m	82%	88	85	85	84	83	85%
6	Mistral NeMO	$0.0003	9.8s	80%	88	88	84	83	81	85%
14	Writer: Palmyra X5	$0.011	23.9s	79%	89	84	83	83	82	84%
13	Z.AI GLM 4.6	$0.0069	46.0s	81%	87	86	85	84	79	84%
16	Claude Haiku 4.5	$0.011	23.8s	79%	88	86	82	82	82	84%
11	o4 Mini	$0.014	23.5s	81%	86	85	84	84	81	84%
29	o4 Mini High	$0.020	37.2s	77%	88	88	83	81	80	84%
28	Cohere Command R+ (Aug. 2024)	$0.020	43.0s	78%	89	84	83	82	81	84%
20	Z.AI GLM 4.7	$0.0092	58.9s	80%	86	85	84	82	80	84%
8	Ministral 3B	$0.0001	4.9s	79%	88	84	83	81	81	84%
37	Claude Sonnet 4	$0.034	50.9s	80%	87	84	83	82	81	83%
26	Z.AI GLM 5	$0.0083	1.2m	78%	88	83	83	81	80	83%
10	Ministral 8B	$0.0004	17.2s	79%	86	85	83	83	79	83%
15	Hermes 3 70B	$0.0006	49.8s	79%	86	83	83	82	80	83%
22	Z.AI GLM 4.7 Flash	$0.0018	1.5m	81%	84	84	83	83	80	83%
12	Mistral Small Creative	$0.0007	11.0s	78%	87	84	82	82	79	83%
51	Gemini 2.5 Pro	$0.039	40.6s	75%	88	83	82	82	74	82%
19	Qwen 3.5 Plus (2026-02-15)	$0.0052	29.5s	79%	84	83	83	80	78	81%
24	Qwen 2.5 72B	$0.0009	37.0s	76%	87	83	82	78	77	81%
30	GPT-4o, Aug. 6th (temp=1)	$0.017	27.8s	78%	84	83	82	81	76	81%
41	Hermes 3 405B	$0.0022	1.6m	76%	84	83	80	80	79	81%
21	Stealth: Aurora Alpha	$0.0000	8.6s	75%	86	80	78	–	–	81%
25	GPT-4o, Aug. 6th (temp=0)	$0.015	23.6s	78%	84	82	82	79	77	81%
42	GPT-4o, May 13th (temp=0)	$0.025	14.4s	75%	84	83	79	79	78	81%
33	DeepSeek-V2 Chat	$0.0018	50.7s	75%	87	82	81	78	76	81%
23	GPT-4o Mini (temp=0)	$0.0012	32.7s	77%	84	81	80	78	78	80%
27	Z.AI GLM 4.5	$0.0050	45.5s	78%	83	82	81	78	78	80%
55	Claude 3.7 Sonnet	$0.039	45.9s	73%	84	82	79	75	75	79%
46	Gemini 2.5 Flash	$0.0062	12.8s	68%	86	85	80	78	66	79%
56	Llama 3.1 8B	$0.0005	3.7m	76%	81	80	79	78	77	79%
34	GPT-4.1 Mini	$0.0023	14.4s	73%	85	79	79	77	75	79%
50	GPT-4o, May 13th (temp=1)	$0.026	13.7s	72%	83	82	77	76	74	79%
38	Gemini 2.5 Flash Lite	$0.0009	12.4s	73%	82	81	77	74	74	78%
43	GPT-5 Nano	$0.0039	1.2m	77%	78	78	78	78	76	78%
35	GPT-4o Mini (temp=1)	$0.0012	29.9s	75%	80	79	79	76	75	78%
44	Llama 3.1 Nemotron 70B	$0.0023	35.4s	73%	82	78	76	75	74	77%
40	WizardLM 2 8x22b	$0.0016	24.8s	74%	79	78	77	75	74	77%
49	Claude 3 Haiku	$0.0020	15.2s	70%	78	77	74	72	70	74%
53	GPT-4.1 Nano	$0.0006	11.1s	70%	76	73	73	72	71	73%
83.08%

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)