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.

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
2	Claude Sonnet 4.5	$0.027	34.3s	92%	97	96	96	92	92	95%
5	Qwen 3.5 397B A17B	$0.015	1.5m	91%	95	94	94	93	92	94%
1	Claude 3.5 Haiku	$0.0034	17.3s	90%	93	93	92	91	91	92%
41	Claude Opus 4.6	$0.069	1.2m	87%	95	93	91	91	87	91%
6	Z.AI GLM 5	$0.0067	48.5s	85%	94	94	92	91	85	91%
39	Claude Opus 4.5	$0.065	57.5s	85%	95	94	92	87	85	91%
9	Claude Haiku 4.5	$0.0093	19.7s	82%	97	92	90	89	84	90%
18	Claude Sonnet 4	$0.025	38.1s	84%	94	93	93	91	80	90%
40	Rocinante 12B	$0.0031	2.6m	80%	98	92	88	86	84	90%
7	GPT-5 Mini	$0.011	42.4s	87%	92	90	89	89	88	90%
12	Writer: Palmyra X5	$0.011	22.5s	83%	94	93	89	86	85	90%
25	Gemini 2.5 Pro	$0.038	38.0s	83%	93	92	91	90	81	89%
56	GPT-5	$0.073	3.0m	87%	91	90	89	89	87	89%
10	Mistral Large 2	$0.011	28.8s	85%	92	90	89	89	86	89%
4	Ministral 3B	$0.0001	5.6s	84%	93	91	89	87	85	89%
3	Ministral 8B	$0.0002	8.4s	85%	93	89	89	87	86	89%
26	Llama 3.1 8B	$0.0003	59.7s	75%	98	96	90	81	79	89%
14	Z.AI GLM 4.6	$0.0076	35.5s	83%	91	91	88	87	84	88%
19	Z.AI GLM 4.5	$0.0046	39.1s	80%	95	90	89	85	81	88%
11	Mistral Small Creative	$0.0007	10.9s	82%	92	91	88	85	83	88%
15	Z.AI GLM 4.7 Flash	$0.0015	1.1m	85%	90	88	87	87	86	88%
8	Gemini 3 Flash (Preview)	$0.0066	17.3s	85%	89	88	88	86	86	87%
16	Mistral Large	$0.012	33.0s	84%	91	89	89	85	83	87%
22	DeepSeek-V2 Chat	$0.0015	33.0s	76%	96	91	87	86	76	87%
53	GPT-5.2	$0.054	1.5m	79%	95	89	87	83	83	87%
29	WizardLM 2 8x22b	$0.0018	24.7s	72%	100	95	94	78	68	87%
34	Claude 3.7 Sonnet	$0.037	46.5s	82%	92	90	88	83	83	87%
52	GPT-5.1	$0.060	1.5m	82%	92	87	86	85	85	87%
38	Z.AI GLM 4.7	$0.0098	2.0m	82%	90	88	85	85	84	86%
13	Qwen 3.5 Plus (2026-02-15)	$0.0049	25.3s	85%	88	87	87	86	84	86%
43	Gemini 3 Pro (Preview)	$0.049	49.2s	83%	89	87	86	86	84	86%
17	Gemini 2.5 Flash Lite	$0.0008	9.4s	79%	92	88	85	85	81	86%
31	GPT-4.1	$0.018	46.3s	79%	92	88	85	85	80	86%
20	Gemini 2.5 Flash	$0.0039	8.1s	78%	92	89	88	86	75	86%
50	MoonshotAI: Kimi K2.5	$0.016	2.5m	82%	87	87	86	85	82	85%
44	Claude 3.5 Sonnet	$0.042	38.5s	79%	89	88	84	83	81	85%
35	o4 Mini High	$0.022	37.6s	79%	88	85	83	82	80	84%
28	Llama 3.1 Nemotron 70B	$0.0021	29.8s	77%	88	87	84	80	79	84%
21	GPT-4o Mini (temp=0)	$0.0011	26.3s	81%	86	84	83	82	82	83%
49	Hermes 3 405B	$0.0022	1.5m	74%	89	88	81	80	78	83%
27	Llama 3.1 70B	$0.0007	23.3s	77%	87	85	84	83	76	83%
36	Hermes 3 70B	$0.0006	45.2s	75%	90	85	84	82	74	83%
32	o4 Mini	$0.014	22.1s	78%	87	85	83	81	77	83%
23	GPT-4o Mini (temp=1)	$0.0011	23.6s	79%	86	84	83	82	78	83%
55	Cohere Command R+ (Aug. 2024)	$0.021	2.1m	75%	89	85	82	80	76	82%
47	GPT-4o, Aug. 6th (temp=1)	$0.015	30.5s	73%	89	85	80	79	78	82%
45	GPT-4o, May 13th (temp=1)	$0.028	14.2s	76%	87	83	81	80	78	82%
51	GPT-4o, May 13th (temp=0)	$0.026	13.3s	73%	90	83	81	81	74	82%
33	Claude 3 Haiku	$0.0021	15.8s	75%	88	82	80	79	78	82%
30	GPT-4.1 Nano	$0.0006	10.0s	75%	85	84	80	80	79	82%
42	Mistral NeMO	$0.0005	20.5s	73%	87	84	81	76	75	80%
24	Stealth: Aurora Alpha	$0.0000	16.4s	80%	81	81	80	–	–	80%
46	Qwen 2.5 72B	$0.0008	39.1s	72%	88	80	79	79	76	80%
37	GPT-4.1 Mini	$0.0025	14.4s	75%	85	80	80	79	76	80%
48	GPT-4o, Aug. 6th (temp=0)	$0.016	21.9s	75%	84	80	80	80	74	80%
54	GPT-5 Nano	$0.0044	1.6m	74%	78	77	76	76	74	76%
86.08%

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)