Run: 2026-03-11-01KKFCGFNB8S4VT2W6ZN29B88A

Run Details

Model:: Qwen 3.5 9B
Test:: Bad Writing Habits
Scenario:: Mystery: examining a crime scene
Duration:: 7m 38s
Cost:: $0.004915
Provider:: Together

Evaluation summary

Score	Evaluator	Details Link
100.00%	Adverbs in dialogue tags	(details)
100.00%	AI-ism adverb frequency	(details)
100.00%	AI-ism character names	(details)
100.00%	AI-ism location names	(details)
83.53%	AI-ism word frequency	(details)
100.00%	Cliché density	(details)
100.00%	Emotion telling (show vs. tell)	(details)
100.00%	Filter word density	(details)
100.00%	Gibberish response detection	(details)
100.00%	Markdown formatting overuse	(details)
100.00%	Missing dialogue indicators (quotation marks)	(details)
27.51%	Name drop frequency	(details)
100.00%	Narrator intent-glossing	(details)
100.00%	"Not X but Y" pattern overuse	(details)
100.00%	Overuse of "that" (subordinate clause padding)	(details)
100.00%	Paragraph length variance	(details)
98.38%	Passive voice overuse	(details)
100.00%	Past progressive (was/were + -ing) overuse	(details)
100.00%	Em-dash & semicolon overuse	(details)
100.00%	Purple prose (modifier overload)	(details)
100.00%	Repeated phrase echo	(details)
81.10%	Sentence length variance	(details)
28.63%	Sentence opener variety	(details)
45.05%	Adverb-first sentence starts	(details)
14.59%	Pronoun-first sentence starts	(details)
0.00%	Subject-first sentence starts	(details)
0.00%	Subordinate conjunction sentence starts	(details)
100.00%	Technical jargon density	(details)
100.00%	Useless dialogue additions	(details)
100.00%	Dialogue tag variety (said vs. fancy)	(details)
82.6263%	Overall

Model input

System

You are an expert fiction writer.

Always keep the following rules in mind:
- Write in past tense and use General English spelling, grammar, and colloquialisms/slang.
- Write in active voice
- Always follow the "show, don't tell" principle.
- Avoid adverbs and cliches and overused/commonly used phrases. Aim for fresh and original descriptions.
- Convey events and story through dialogue.
- Mix short, punchy sentences with long, descriptive ones. Drop fill words to add variety.
- Skip "he/she said said" dialogue tags and convey people's actions or face expressions through their speech
- Avoid mushy dialog and descriptions, have dialogue always continue the action, never stall or add unnecessary fluff. Vary the descriptions to not repeat yourself.
- Put dialogue on its own paragraph to separate scene and action.
- Reduce indicators of uncertainty like "trying" or "maybe"

When writing text:
- NEVER conclude the scene on your own, follow the beat instructions very closely.
- NEVER end with foreshadowing.
- NEVER write further than what I prompt you with.
- AVOID imagining possible endings, NEVER deviate from the instructions.
- STOP EARLY if the continuation contains what was required in the instructions. You do not need to fill out the full amount of words possible.

User/Human

Take into account the following glossary of characters/locations/items/lore... when writing your response:
<codex>
<character id="4416" name="Detective Harlow Quinn" aliases="Quinn, Detective Quinn, Harlow" pronouns="she/her" species="Human" storyRole="Antagonist">
  <eyeColor>brown</eyeColor>
  <hair>closely cropped salt-and-pepper</hair>
  <height>5'9"</height>
  <age>41</age>
  <jawline>sharp jaw</jawline>
  <watch>worn leather watch on her left wrist</watch>
  <bearing>military precision</bearing>
  <description>A Metropolitan Police detective with 18 years of decorated service who suspects the clique is involved in criminal activity.</description>
  <backstory>She lost her partner, DS Morris, during a case three years ago under unexplained circumstances that had supernatural origins she doesn't yet understand.</backstory>
</character>

<character id="4414" name="Eva Kowalski" aliases="Eva, Evie" pronouns="she/her" species="Human" storyRole="Best Friend">
  <eyeColor>green</eyeColor>
  <hair>curly red</hair>
  <height>5'4"</height>
  <age>26</age>
  <glasses>round glasses</glasses>
  <satchel>worn leather satchel full of books</satchel>
  <freckles>freckled complexion</freckles>
  <nervousHabit>tucking hair behind her left ear</nervousHabit>
  <description>Aurora's childhood friend and an occult researcher.</description>
  <backstory>Moved to London two years before Aurora and works as a research assistant at the British Museum's restricted archives. She holds a master's degree in Ancient History from Oxford.</backstory>
</character>

<location id="856" name="The Veil Market" aliases="Veil Market, the Market, underground market" realm="Earth">
  <currentLocation>abandoned Tube station beneath Camden</currentLocation>
  <entryRequirement>bone token</entryRequirement>
  <schedule>moves locations every full moon</schedule>
  <description>A hidden supernatural black market that sells enchanted goods, banned alchemical substances, and information.</description>
</location>

<item id="2004" name="Veil Compass" aliases="the Compass, shadow compass" type="Tool" origin="The Veil Market">
  <casingMaterial>small brass compass</casingMaterial>
  <faceMarkings>face etched with protective sigils</faceMarkings>
  <needle>points toward the nearest supernatural rift or portal</needle>
  <patina>casing has a patina of verdigris</patina>
  <creator>crafted by a Shade artisan</creator>
  <description>A compass attuned to supernatural energy.</description>
</item>
</codex>

Continue the story using the following instructions:
<instructions>
Write a fully fleshed out scene of at least 1000 words in the mystery genre.

A detective arrives at a crime scene in an unusual location. Something is wrong — the evidence doesn't add up. A colleague is present, offering a different interpretation. Through careful observation and deduction, the detective begins to see what others have missed.

Use the codex entries above as your world reference for characters and setting.
Only include the prose of the scene without any markdown or commentary.
</instructions>

Model response

Harlow Quinn stepped over the heavy iron railing. Dust coated the floor in a thick gray layer. She scanned the tracks with tired eyes. The tunnel swallowed the light from the single overhead bulb.

"Check the corpse," said the voice behind her.

Eva Kowalski stood on the platform. A worn leather satchel hung from her shoulder. Curly red hair bounced with her movement. She adjusted her round glasses.

I put on a coat made of thick canvas. The collar turned up to hide the face. I walked closer. The metal of the train tracks vibrated at my boots.

"Blood on the floor," Quinn said. She looked at the body. It lay in a heap of clothes. A red tie knotted the collar.

Eva reached into her bag. A book about Ancient History fell out. She picked it up.

"No blood on the floor," Quinn said.

She knelt on the cold stone. Her hand touched the ground. Grime clung to her fingers.

"The train was moving the body," Eva said. "The tracks were empty."

I looked at the tracks. They were empty. The tracks were dark.

"The floor was wet," I said. "It was painted on top of the grime."

Eva crouched beside Quinn. Her green eyes focused on the jersey of the corpse.

"It is evidence," Quinn said. "It proves the train stopped."

"The engine didn't stop," Eva said. "The tracks moved."

I stood. The watch on my left wrist was worn. The leather band was cracked. It had marched with me for eighteen years.

The Veil Compass lay in the mud. It was small brass. The casing was covered in verdigris.

"Your compass," I said.

I picked it up. The needle pointed at the wall.

"I brought the tool," Eva said. "It points to the rift."

The needle twitched. Then it stopped spinning.

"The movement is the key," I said.

I looked at the split in the wall. It was wide. It ran deep.

"The corpse fell in," I said.

"The corpse is not here," Eva said. "The body is gone."

I grabbed her arm. She pulled it away. Her grip was firm.

"You think," I said. "You see."

"The shadow stays," Eva said. "The shadow does not pay."

I looked at the wall. The paint was peeling. The plaster felt soft.

"The paint is dry," Eva said. "The paint is not dry."

"It is dried." I touched the wall. My knuckles were white.

"The glass is broken," I said. "The glass is not broken."

"Who broke it?" I asked.

I took the glass shards from the floor. They were sharp. Edges ran clean.

"The glass is the key," Eva said. "It is the time."

"The time stops," I said. "The time moves."

I checked my watch. The hands moved backward. The minute hand ticked counter-clockwise.

I froze. My breath caught in my throat.

"Your watch," I said.

I held the metal band. It was cold.

"Morris," I said.

I thought of the partner I lost. The partner I buried. The partner I didn't understand.

"The watch does not lie," Eva said. "The watch is the truth."

I looked at the corpse. The corpse was gone. I looked at the wall. The wall was the truth.

"The wall breathes," I said. "The wall dies."

"Eva," I said.

I looked at her face. Her green eyes were wide.

"The market," I said. "The market is here."

I dropped the gun from my pocket. It hit the floor with a clink.

The needle spun. The needle stopped.

I stood. The tunnel grew cold. The air was thick. I stood still.

"The Veil opens," I said.

The door closed.

Evaluation details

Result

Evaluator

Details

Meta Data

100.00%

Adverbs in dialogue tags

Target: ≤10% dialogue tags with adverbs

totalTags	26
adverbTagCount	0
adverbTags	(empty)
dialogueSentences	42
tagDensity	0.619
leniency	1
rawRatio	0
effectiveRatio	0

100.00%

AI-ism adverb frequency

Target: <2% AI-ism adverbs (58 tracked)

wordCount	607
totalAiIsmAdverbs	0
found	(empty)
highlights	(empty)

100.00%

AI-ism character names

Target: 0 AI-default names (17 tracked, −20% each)

codexExemptions	(empty)
found	(empty)

100.00%

AI-ism location names

Target: 0 AI-default location names (33 tracked, −20% each)

codexExemptions	(empty)
found	(empty)

83.53%

AI-ism word frequency

Target: <2% AI-ism words (290 tracked)

wordCount

607

totalAiIsms

found

word	"scanned"
count	1

word	"vibrated"
count	1

highlights

0	"scanned"
1	"vibrated"

100.00%

Cliché density

Target: ≤1 cliche(s) per 800-word window

totalCliches	0
maxInWindow	0
found	(empty)
highlights	(empty)

100.00%

Emotion telling (show vs. tell)

Target: ≤3% sentences with emotion telling

emotionTells	0
narrationSentences	102
matches	(empty)

100.00%

Filter word density

Target: ≤3% sentences with filter/hedge words

filterCount

hedgeCount

narrationSentences

102

filterMatches

"watch"

hedgeMatches

(empty)

100.00%

Gibberish response detection

Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)

analyzedSentences	117
gibberishSentences	0
adjustedGibberishSentences	0
longSentenceCount	0
runOnParagraphCount	0
giantParagraphCount	0
wordSaladCount	0
repetitionLoopCount	0
controlTokenCount	0
maxSentenceWordsSeen	10
ratio	0
matches	(empty)

100.00%

Markdown formatting overuse

Target: ≤5% words in markdown formatting

markdownSpans	0
markdownWords	0
totalWords	607
ratio	0
matches	(empty)

100.00%

Missing dialogue indicators (quotation marks)

Target: ≤10% speech attributions without quotation marks

totalAttributions	26
unquotedAttributions	0
matches	(empty)

27.51%

Name drop frequency

Target: ≤1.0 per-name mentions per 100 words

totalMentions

wordCount

449

uniqueNames

maxNameDensity

2.45

worstName

"Eva"

maxWindowNameDensity

worstWindowName

"Eva"

discoveredNames

Quinn	5
Eva	11
Kowalski	1
Ancient	1
History	1
Veil	1
Compass	1

persons

0	"Quinn"
1	"Eva"
2	"Kowalski"
3	"History"
4	"Compass"

places

(empty)

globalScore

0.275

windowScore

0.333

100.00%

Narrator intent-glossing

Target: ≤2% narration sentences with intent-glossing patterns

analyzedSentences	26
glossingSentenceCount	0
matches	(empty)

100.00%

"Not X but Y" pattern overuse

Target: ≤1 "not X but Y" per 1000 words

totalMatches	0
per1kWords	0
wordCount	607
matches	(empty)

100.00%

Overuse of "that" (subordinate clause padding)

Target: ≤2% sentences with "that" clauses

thatCount	0
totalSentences	117
matches	(empty)

100.00%

Paragraph length variance

Target: CV ≥0.5 for paragraph word counts

totalParagraphs

mean

11.67

std

6.49

0.556

sampleLengths

0	34
1	8
2	26
3	30
4	24
5	16
6	7
7	16
8	12
9	12
10	14
11	14
12	10
13	9
14	23
15	17
16	4
17	10
18	11
19	7
20	7
21	14
22	6
23	11
24	12
25	6
26	10
27	13
28	11
29	11
30	11
31	5
32	14
33	11
34	8
35	13
36	8
37	4
38	8
39	3
40	16
41	12
42	19
43	8
44	3
45	10
46	8
47	14
48	6
49	13

98.38%

Passive voice overuse

Target: ≤2% passive sentences

passiveCount

totalSentences

102

matches

0	"was covered"
1	"was gone"

100.00%

Past progressive (was/were + -ing) overuse

Target: ≤2% past progressive verbs

pastProgressiveCount

totalVerbs

107

matches

0	"was peeling"

100.00%

Em-dash & semicolon overuse

Target: ≤2% sentences with em-dashes/semicolons

emDashCount	0
semicolonCount	0
flaggedSentences	0
totalSentences	117
ratio	0
matches	(empty)

100.00%

Purple prose (modifier overload)

Target: <4% adverbs, <2% -ly adverbs, no adj stacking

wordCount	450
adjectiveStacks	0
stackExamples	(empty)
adverbCount	6
adverbRatio	0.013333333333333334
lyAdverbCount	1
lyAdverbRatio	0.0022222222222222222

100.00%

Repeated phrase echo

Target: ≤20% sentences with echoes (window: 2)

totalSentences	117
echoCount	0
echoWords	(empty)

81.10%

Sentence length variance

Target: CV ≥0.4 for sentence word counts

totalSentences

117

mean

5.19

std

1.83

0.353

sampleLengths

0	8
1	9
2	7
3	10
4	8
5	6
6	8
7	7
8	5
9	9
10	8
11	3
12	10
13	6
14	5
15	7
16	6
17	5
18	7
19	4
20	7
21	6
22	5
23	5
24	8
25	4
26	5
27	3
28	4
29	6
30	8
31	4
32	10
33	5
34	5
35	6
36	3
37	2
38	8
39	5
40	8
41	7
42	4
43	6
44	4
45	4
46	6
47	6
48	5
49	3

28.63%

Sentence opener variety

Target: ≥60% unique sentence openers

consecutiveRepeats	25
diversityRatio	0.18803418803418803
totalSentences	117
uniqueOpeners	22

45.05%

Adverb-first sentence starts

Target: ≥3% sentences starting with an adverb

adverbCount

totalSentences

matches

0	"Then it stopped spinning."

ratio

0.014

14.59%

Pronoun-first sentence starts

Target: ≤30% sentences starting with a pronoun

pronounCount

totalSentences

matches

0	"She scanned the tracks with"
1	"She adjusted her round glasses."
2	"I put on a coat"
3	"I walked closer."
4	"She looked at the body."
5	"It lay in a heap"
6	"She picked it up."
7	"She knelt on the cold"
8	"Her hand touched the ground."
9	"I looked at the tracks."
10	"They were empty."
11	"Her green eyes focused on"
12	"It had marched with me"
13	"It was small brass."
14	"I picked it up."
15	"I looked at the split"
16	"It was wide."
17	"It ran deep."
18	"I grabbed her arm."
19	"She pulled it away."

ratio

0.514

0.00%

Subject-first sentence starts

Target: ≤72% sentences starting with a subject

subjectCount

totalSentences

matches

0	"Harlow Quinn stepped over the"
1	"Dust coated the floor in"
2	"She scanned the tracks with"
3	"The tunnel swallowed the light"
4	"Eva Kowalski stood on the"
5	"A worn leather satchel hung"
6	"She adjusted her round glasses."
7	"I put on a coat"
8	"The collar turned up to"
9	"I walked closer."
10	"The metal of the train"
11	"She looked at the body."
12	"It lay in a heap"
13	"A red tie knotted the"
14	"Eva reached into her bag."
15	"A book about Ancient History"
16	"She picked it up."
17	"She knelt on the cold"
18	"Her hand touched the ground."
19	"Grime clung to her fingers."

ratio

0.959

0.00%

Subordinate conjunction sentence starts

Target: ≥2% sentences starting with a subordinating conjunction

subConjCount	0
totalSentences	74
matches	(empty)
ratio	0

100.00%

Technical jargon density

Target: ≤6% sentences with technical-jargon patterns

analyzedSentences	3
technicalSentenceCount	0
matches	(empty)

100.00%

Useless dialogue additions

Target: ≤5% dialogue tags with trailing filler fragments

totalTags	26
uselessAdditionCount	0
matches	(empty)

100.00%

Dialogue tag variety (said vs. fancy)

Target: ≤10% fancy dialogue tags

totalTags	25
fancyCount	0
fancyTags	(empty)
dialogueSentences	42
tagDensity	0.595
leniency	1
rawRatio	0
effectiveRatio	0

82.6263%