Run: 2026-03-11-01KKFD0AHKH98B9GB9P2EC6XKC

Run Details

Model:
Qwen 3.5 9B
Test:
Bad Writing Habits
Scenario:
Mystery: examining a crime scene
Duration:
2m 37s
Cost:
$0.001427
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)
100.00% 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)
0.00% 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)
93.57% 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)
100.00% Sentence length variance (details)
25.00% Sentence opener variety (details)
0.00% Adverb-first sentence starts (details)
95.00% 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)
83.7856% 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

AI
Rain dripped from the rusted ceiling of the abandoned Tube station. The air smelled of wet limestone and old copper. Harlow Quinn stepped over the police tape, her boots snapping into the damp concrete. Her left wrist tapped against her thigh. "Youain't blind," Eva Kowalski said. She adjusted her glasses, tucking curly red hair behind her left ear. "Blindness comes from being too clear seeing," Harlow replied. "I see the blood is missing." "It's not blood," Eva said. She knelt beside the body. "It's grime." "The body is warm," Harlow said. "It is not," Eva corrected. "It is the temperature of death." "Death does not always bring cold. Look at the stitch." The corpse wore a grey uniform. The front of the jacket was ripped open, but the heart had not been extracted. The chest cavity remained intact, untouched by claw or knife. "The wound on the neck is clean," Harlow said. "The wound is not on the neck." "Stop looking at the face." Eva looked up. Her green eyes widened behind the lenses. "It is the market." "The market is closed." "It moves," Eva said. "You saw the token on the ticket." "The token is for the gate." "The token is for the floor." "The floor is not the market." "The floor is the market," Eva said. "Look at the floor." "The floor is stone." "The floor is not stone." "It is metal." "It is flesh." "Eva," Harlow said. "I am the detective. You are the witness." "You are the witness," Eva said. "I am the researcher." "The needles lie." "Needles do not lie." "The compass is broken." "The compass is fixed." "Show me." Harlow slid the Veil Compass from her pocket. Brass casing covered in verdigris. The needle twitched. It pointed straight at the wall. "I am not a trick," Harlow said. "I am a lie." "You are a truth," Eva said. "You are a thing." "Show me the market." "It closed," Eva said. "It moved." "The need points," Harlow said. "To the wall." "Show me the wall," Eva said. "It is stone." "The wall is the market." "The wall is stone." "It is both." "It is neither." "Show me the body." "Show me the blood." "Show me the market." "I am not seeing anything." "You are seeing everything." "Stop the needle." "It cannot stop." "It is metal." "It is magic." "It is brass." "It is alive." "It is broken." "It is working." "Show me the door." "The door is closed." "The door is locked." "The door is open." "It is closed." "I need the market." "It is here." "It is not here." "It is gone." "It is open." "It is closed." "We are gone." "We are not gone." "I am gone." "You are not gone." "I am here." "You are not here." "I am here." "You are here." "I am gone." "I have to go." "I must stay." "It is open." "It is closed." "It is the market." "It is not the market." "It is the death." "It is the life." "It is the need." "It is the spike." "It is the wall." "It is the needle."
created_at"2026-03-11T21:31:50.225Z" 3/11/2026, 9:31:50 PM
model"qwen/qwen3.5-9b-20260310"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency328
moderation_latency(null)
generation_time156605
tokens_prompt1149
tokens_completion8958
native_tokens_prompt1100
native_tokens_completion8779
native_tokens_completion_images(null)
native_tokens_reasoning8108
native_tokens_cached0
num_media_prompt(null)
num_input_audio_prompt(null)
num_media_completion0
num_search_results(null)
origin"https://ncbench.com/"
is_byokfalse
finish_reason"stop"
native_finish_reason"stop"
usage0.00142685
router(null)
provider_responses
0
endpoint_id"00d506d9-a5e9-4382-a2b9-d54732365594"
id"oagL9nM-3pDw3Z-9dadab1721e8f03c"
is_byokfalse
latency328
model_permaslug"qwen/qwen3.5-9b-20260310"
provider_name"Together"
status200
user_agent"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer(null)
api_type"completions"
id"gen-1773264710-X2gCDeTNPN2Evo3PG9dp"
upstream_id"oagL9nM-3pDw3Z-9dadab1721e8f03c"
total_cost0.00142685
cache_discount(null)
upstream_inference_cost0
provider_name"Together"

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags15
adverbTagCount0
adverbTags(empty)
dialogueSentences94
tagDensity0.16
leniency0.319
rawRatio0
effectiveRatio0
100.00% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount520
totalAiIsmAdverbs0
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)
100.00% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount520
totalAiIsms0
found(empty)
highlights(empty)
100.00% Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches1
maxInWindow1
found
0
label"eyes widened/narrowed"
count1
highlights
0"eyes widened"
100.00% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells0
narrationSentences30
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount0
narrationSentences30
filterMatches(empty)
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences109
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen15
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords520
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions16
unquotedAttributions0
matches(empty)
0.00% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions23
wordCount152
uniqueNames7
maxNameDensity6.58
worstName"Eva"
maxWindowNameDensity5
worstWindowName"Eva"
discoveredNames
Tube1
Quinn1
Kowalski1
Eva10
Harlow8
Veil1
Compass1
persons
0"Quinn"
1"Kowalski"
2"Eva"
3"Harlow"
places(empty)
globalScore0
windowScore0
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences11
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount520
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences109
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs85
mean6.12
std5.92
cv0.968
sampleLengths
041
117
215
312
46
511
610
731
89
97
105
1114
124
1311
146
156
166
1711
184
195
203
213
2211
2310
243
254
264
274
282
2922
3011
3110
324
336
348
359
365
374
383
393
404
414
424
435
444
453
463
473
483
493
93.57% Passive voice overuse
Target: ≤2% passive sentences
passiveCount1
totalSentences30
matches
0"was ripped"
1"been extracted"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs37
matches(empty)
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences109
ratio0
matches(empty)
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount152
adjectiveStacks0
stackExamples(empty)
adverbCount0
adverbRatio0
lyAdverbCount1
lyAdverbRatio0.006578947368421052
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences109
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences109
mean4.77
std2.35
cv0.492
sampleLengths
011
19
214
37
45
512
69
76
85
95
102
116
125
136
1410
156
1615
1710
189
197
205
213
227
234
244
254
267
276
286
296
307
314
324
335
343
353
363
378
386
394
403
414
424
434
442
458
465
473
486
497
25.00% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats42
diversityRatio0.1743119266055046
totalSentences109
uniqueOpeners19
0.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount0
totalSentences16
matches(empty)
ratio0
95.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount5
totalSentences16
matches
0"Her left wrist tapped against"
1"She adjusted her glasses, tucking"
2"She knelt beside the body."
3"Her green eyes widened behind"
4"It pointed straight at the"
ratio0.313
0.00% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount16
totalSentences16
matches
0"Rain dripped from the rusted"
1"The air smelled of wet"
2"Harlow Quinn stepped over the"
3"Her left wrist tapped against"
4"Eva Kowalski said"
5"She adjusted her glasses, tucking"
6"She knelt beside the body."
7"The corpse wore a grey"
8"The front of the jacket"
9"The chest cavity remained intact,"
10"Eva looked up."
11"Her green eyes widened behind"
12"Harlow slid the Veil Compass"
13"Brass casing covered in verdigris."
14"The needle twitched."
15"It pointed straight at the"
ratio1
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences16
matches(empty)
ratio0
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences5
technicalSentenceCount0
matches(empty)
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags15
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags15
fancyCount1
fancyTags
0"Eva corrected (correct)"
dialogueSentences94
tagDensity0.16
leniency0.319
rawRatio0.067
effectiveRatio0.021
83.7856%