Run: 2026-02-19-01KHTR30MQFT8ZNGGA08HDJ8GN

Run Details

Model:
Hermes 3 405B
Test:
Bad Writing Habits
Scenario:
Mystery: examining a crime scene
Duration:
26.8s
Cost:
$0.001733
Provider:
DeepInfra

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)
14.77% 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)
20.32% 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)
85.83% Paragraph length variance (details)
100.00% Passive voice overuse (details)
24.56% Past progressive (was/were + -ing) overuse (details)
89.95% Em-dash & semicolon overuse (details)
100.00% Purple prose (modifier overload) (details)
100.00% Repeated phrase echo (details)
100.00% Sentence length variance (details)
100.00% Sentence opener variety (details)
0.00% Adverb-first sentence starts (details)
64.44% Pronoun-first sentence starts (details)
71.11% Subject-first sentence starts (details)
0.00% Subordinate conjunction sentence starts (details)
100.00% Technical jargon density (details)
75.00% Useless dialogue additions (details)
13.64% Dialogue tag variety (said vs. fancy) (details)
78.6539% 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
Detective Harlow Quinn ducked under the caution tape stretched across the entrance to the abandoned Tube station. The air smelled of damp earth and rusting metal. She descended the worn stairs, her polished shoes echoing on the concrete. "Detective Quinn," a familiar voice called out. "Over here." Harlow turned to see her partner, DS Morris, waving her over to the far wall. She strode closer, noting his grim expression. "What have we got?" she asked, voice crisp. "Eyewitnesses reported seeing a group of people entering the station just before the screams started," Morris said. "Some sort of secret market, they claim. Though there's no trace of it now." Harlow frowned, scanning the empty platform. Moisture dripped from the tiled ceiling, pooling in cracks in the cement. "No stalls or merchandise left behind?" "Not a scrap," Morris sighed. "Place is clean as a whistle. Except for this." He led her to an archway leading to the old train tracks. Flickering fluorescent lights cast eerie shadows. Harlow crouched down, examining the dark streaks staining the grimy floor. "Blood," she murmured, glancing up at Morris. "A lot of it." "And no body," he said. "We've searched the tunnels, but there's nothing. It's like they just vanished. Or were taken." A chill ran down Harlow's spine. She stood, dusting off her slacks. "I want a full forensics team down here. And round up those witnesses. See if they remember anything useful." As Morris radioed the orders in, Harlow paced the platform, her mind racing. She'd heard the rumors of hidden black markets dealing in illicit goods. The Veil Market - it matched the descriptions. Dangerous, enchanted items traded on the fringes of society. But this... She paused at a glint of metal near the tracks. Crouching down, she picked up a small brass compass. Faded markings etched the face, the needle spinning erratically. Pocketing it, she rejoined her partner. "Forensics is on their way," he said. "And uniforms are tracking down the witnesses now. You find something?" "Perhaps," Harlow replied. "This Veil Market sounds organized. Not the type to leave evidence or witnesses behind. But they may have slipped up." The detective regarded the bloodied stones a moment longer before turning on her heel. "We need to dig into the archives, see if there's any record of similar incidents. And track down some of these enchanted relics the market is said to trade in." "It's a start," Morris agreed, falling into step beside her. His gaze was troubled. "You think this is supernatural? Like..." He trailed off, but Harlow knew what he was thinking. Three years ago, they'd lost a good man to forces beyond their understanding. She clenched her fist, the compass digging into her palm. "I don't know," she said quietly. "But I intend to find out." Their footsteps echoed as they climbed back into the gray London daylight. Harlow blinked in the sudden brightness, slipping on her sunglasses. Whatever they were dealing with, she would get to the bottom of it. She had to. The cost of failure was too high. And in her pocket, the compass needle spun, pointing insistently toward the full moon rising over the city skyline.
created_at"2026-02-19T10:45:47.803Z" 2/19/2026, 10:45:47 AM
model"nousresearch/hermes-3-llama-3.1-405b"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency454
moderation_latency(null)
generation_time26728
tokens_prompt1184
tokens_completion828
native_tokens_prompt1027
native_tokens_completion706
native_tokens_completion_images(null)
native_tokens_reasoning0
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"
usage0.001733
router(null)
provider_responses
0
endpoint_id"3280e8f8-0960-400c-8284-2e03a0bcb446"
id"cmpl-96aa549503394f969f3011618bcba438"
is_byokfalse
latency69
model_permaslug"nousresearch/hermes-3-llama-3.1-405b"
provider_name"DeepInfra"
status200
api_type"completions"
id"gen-1771497947-b1K0uXDU21hKgpwNzqxq"
upstream_id"cmpl-96aa549503394f969f3011618bcba438"
total_cost0.001733
cache_discount(null)
upstream_inference_cost0
provider_name"DeepInfra"

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags10
adverbTagCount1
adverbTags
0"she said quietly [quietly]"
dialogueSentences22
tagDensity0.455
leniency0.909
rawRatio0.1
effectiveRatio0.091
100.00% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount528
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)
14.77% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount528
totalAiIsms9
found
0
word"echoing"
count1
1
word"familiar"
count1
2
word"scanning"
count1
3
word"chill"
count1
4
word"racing"
count1
5
word"glint"
count1
6
word"etched"
count1
7
word"footsteps"
count1
8
word"echoed"
count1
highlights
0"echoing"
1"familiar"
2"scanning"
3"chill"
4"racing"
5"glint"
6"etched"
7"footsteps"
8"echoed"
100.00% Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches1
maxInWindow1
found
0
label"clenched jaw/fists"
count1
highlights
0"clenched her fist"
100.00% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells0
narrationSentences42
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount0
narrationSentences42
filterMatches(empty)
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences54
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen30
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords529
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions11
unquotedAttributions0
matches(empty)
20.32% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions20
wordCount347
uniqueNames7
maxNameDensity2.59
worstName"Harlow"
maxWindowNameDensity3
worstWindowName"Harlow"
discoveredNames
Harlow9
Quinn1
Tube1
Morris6
Veil1
Market1
London1
persons
0"Harlow"
1"Quinn"
2"Morris"
places
0"London"
globalScore0.203
windowScore0.667
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences31
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount529
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences54
matches(empty)
85.83% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs21
mean25.19
std11.35
cv0.45
sampleLengths
038
19
222
38
431
524
614
729
811
920
1031
1144
1234
1318
1423
1544
1620
1733
1812
1945
2019
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount0
totalSentences42
matches(empty)
24.56% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount2
totalVerbs76
matches
0"was thinking"
1"were dealing"
89.95% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount1
semicolonCount0
flaggedSentences1
totalSentences54
ratio0.019
matches
0"The Veil Market - it matched the descriptions."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount346
adjectiveStacks0
stackExamples(empty)
adverbCount5
adverbRatio0.014450867052023121
lyAdverbCount3
lyAdverbRatio0.008670520231213872
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences54
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences54
mean9.8
std5.16
cv0.527
sampleLengths
017
19
212
37
42
515
67
78
817
914
106
1112
126
135
149
1512
166
1711
187
194
205
2115
226
236
2419
2513
2612
278
289
292
3010
319
329
336
347
3511
363
3720
3814
3930
4010
414
426
4310
4413
4510
466
476
4812
4910
100.00% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats0
diversityRatio0.6296296296296297
totalSentences54
uniqueOpeners34
0.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount0
totalSentences36
matches(empty)
ratio0
64.44% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount14
totalSentences36
matches
0"She descended the worn stairs,"
1"She strode closer, noting his"
2"she asked, voice crisp"
3"He led her to an"
4"she murmured, glancing up at"
5"She stood, dusting off her"
6"She'd heard the rumors of"
7"She paused at a glint"
8"His gaze was troubled."
9"He trailed off, but Harlow"
10"She clenched her fist, the"
11"she said quietly"
12"Their footsteps echoed as they"
13"She had to."
ratio0.389
71.11% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount28
totalSentences36
matches
0"Detective Harlow Quinn ducked under"
1"The air smelled of damp"
2"She descended the worn stairs,"
3"a familiar voice called out"
4"Harlow turned to see her"
5"She strode closer, noting his"
6"she asked, voice crisp"
7"Harlow frowned, scanning the empty"
8"Moisture dripped from the tiled"
9"He led her to an"
10"Harlow crouched down, examining the"
11"she murmured, glancing up at"
12"A chill ran down Harlow's"
13"She stood, dusting off her"
14"She'd heard the rumors of"
15"The Veil Market - it"
16"She paused at a glint"
17"The detective regarded the bloodied"
18"Morris agreed, falling into step"
19"His gaze was troubled."
ratio0.778
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences36
matches(empty)
ratio0
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences17
technicalSentenceCount0
matches(empty)
75.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags10
uselessAdditionCount1
matches
0"she asked, voice crisp"
13.64% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags9
fancyCount3
fancyTags
0"Morris sighed (sigh)"
1"she murmured (murmur)"
2"Morris agreed (agree)"
dialogueSentences22
tagDensity0.409
leniency0.818
rawRatio0.333
effectiveRatio0.273
78.6539%