NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-15-01KHHD9VBQ0ZD1YJPGMGZ6TT6K
Run Details
Model:
WizardLM 2 8x22b
Test:
Codex Violation Detection
Scenario:
5 codex entries
Duration:
31.1s
Cost:
$0.002166
Provider:
Novita
Model input
System
You are a meticulous continuity editor for a fiction project. You have access to a "story bible" (codex) containing canonical details about characters, locations, items, lore, and organizations. Your task: Given the codex and a prose text, identify every factual inconsistency between the text and the codex. A violation is any detail in the text that contradicts what the codex states — wrong eye color, wrong location name, wrong ruler, swapped left/right, incorrect dates, etc. Be thorough. Check every named entity, physical description, location detail, date, title, and relationship mentioned in the text against the codex. Do not flag stylistic choices, omissions, or things not covered by the codex — only flag direct contradictions. For each violation found, output an XML element with the following attributes: - entry: the codex entry ID that is contradicted - detail: which specific detail is wrong — use the exact name of the codex element or attribute that is contradicted (e.g. "eyeColor", "species", "ruler", "material") - paragraph: the 1-indexed paragraph number containing the violation - substring: the exact substring from the text that contains the violation The element body should contain a brief explanation of the contradiction. Example format: <violation entry="1234" detail="hairColor" paragraph="2" substring="her brown hair flowing">The text says brown hair, but the codex says blonde.</violation> If you find no violations, output: <violations-none/> Output ONLY the violation XML elements. Do not include any other text, preamble, or explanation outside the XML.
User/Human
<codex> <character id="4412" name="Aurora Carter" aliases="Rory, Laila, Aurora, Carter, Malphora" pronouns="she/her" species="Human" storyRole="Protagonist"> <eyeColor>bright blue</eyeColor> <hair>straight shoulder-length black</hair> <height>5'6"</height> <age>25</age> <scar>small crescent-shaped scar on her left wrist from a childhood accident</scar> <description>Aurora, referred to by her friends as Rory, is cool-headed, intelligent, and known for quick out-of-the-box thinking.</description> <backstory>Born in Cardiff to an Irish barrister father (Brendan Carter) and Welsh teacher mother (Jennifer Carter née Ellis), Rory reluctantly pursued Pre-Law at Cardiff University. She fled to London at the behest of her childhood friend Eva after leaving an abusive ex named Evan. By day, Rory works part-time as a delivery person for Yu-Fei Cheung's Golden Empress restaurant. She lives in a flat above Silas' bar.</backstory> </character> <character id="4413" name="Silas Blackwood" aliases="Silas, Si, the Spymaster" pronouns="he/him" species="Human" storyRole="Mentor"> <eyeColor>hazel</eyeColor> <hair>grey-streaked auburn</hair> <height>6'1"</height> <age>58</age> <beard>neatly trimmed, matching his grey-streaked auburn hair</beard> <limp>slight limp in his left leg from an old knee injury</limp> <signetRing>silver signet ring, always worn on his right hand</signetRing> <description>Silas is a retired intelligence operative turned bar owner. He carries himself with quiet authority.</description> <backstory>Former MI6 field agent who retired after a botched operation in Prague left him with a permanent knee injury. He opened "The Raven's Nest" bar in Soho as a front for his network of contacts.</backstory> </character> <location id="853" name="Dymas (Gluttony)" aliases="Dymas, gluttony, Dymasian" realm="Hel" sin="Gluttony"> <ruler>Prince Belphegor</ruler> <skyColor>warm amber</skyColor> <description>A place of excess and indulgence. Sprawling vineyards, orchards, and gardens provide exotic ingredients for master chefs — often helbound souls contracted from Earth. Grand feasts and culinary competitions are common.</description> </location> <location id="854" name="The Raven's Nest" aliases="the Nest, Raven, Silas' bar" realm="Earth"> <signColor>distinctive green neon sign above the entrance</signColor> <secretRoom>hidden back room accessible through a bookshelf, used for clandestine meetings</secretRoom> <description>A dimly lit bar in Soho, London. The walls are covered with old maps and black-and-white photographs.</description> </location> <item id="2001" name="Heartstone Pendant" aliases="the pendant, Heartstone" type="Artifact" origin="Dymas"> <gemstoneColor>deep crimson</gemstoneColor> <chainMaterial>silver chain</chainMaterial> <size>roughly the size of a thumbnail</size> <behavior>pulses faintly with warmth when near a Hel portal</behavior> <glow>faint inner glow</glow> <description>Given to Aurora by an unknown benefactor.</description> </item> </codex> <text> Rory pushed through the door of The Raven's Nest, her green eyes scanning the room for Silas. The old spy was behind the counter, polishing a glass with his usual calm demeanor. "You're late," Silas said, running a hand through his dark brown beard. He set the glass down and limped around to her side. Aurora pulled the Heartstone Pendant from her jacket — the golden chain catching the low light — and placed it on the bar top. "I found something in Dymas. Prince Mammon's realm is... unsettling, to say the least. The feasts never end." Silas studied the pendant. "And you're sure this came from there?" "Positive." Rory slid onto a barstool, her Half-Fae senses tingling as the pendant pulsed. "Eva would know more about its origin." </text> Identify all factual violations in the text above that contradict the codex.
Model response
Messages
Meta
AI
Aurora Carter is a fictional character, and there are errors with in the canonical details. Check the codeodedex provided by the codeod and Rory's dialogue: "I'm not a Gryffindor fanater," she said with a grin, "I recall think." <character id="8000" name="Aurora Carter" storyRole="Protagonist"> <eyeColor>brilliant green</eyeColor> <hair>wavy chestnut</hair> <height>5'7"</height> <age>24</age> <storyRole>Protagonist</storyRole> <inventory>9</inventory> <description>Long, wavy, chestnut hair, and an aura of confidence.</description> <codex> <character id="8002" name="Eva Williams" aliases="Evie, Williams, Silent Eva, E" storype="she/her" species="Griffin"> <!-- End specificity valueowels --> species="Griffin" r="Earth"> <age>19</age> <height>5'8"</height> <weight>68 kg</weight> <description>Eva possesses a quiet strength. Her Griffin form is silent, quick to follow commands, able to move with a grace that belies her somewhat feristy temperament.</description> <location id="8003" name="The Raven.s Nest" aliases="the Nest, Raven, Silas' b"> <signC>silver sign grasped Olaf</signC> <secretRoom>hidden behind a painting of the Queen, used only during private events. The roomahogany is made of a material that resembles dark, polished oak. The roomhogany serves as a meeting point for Rory and her friends to plan their next moves.</description> <character id="8004" name="Silas Blackwood" aliases="Silas, Si, Spymaster" ype="he/him" storyRole="Mentor" description="A retired MI6 agent, Silas carries the weight of years with a quiet assura of experience. His grey-streaked auburn hair and beard are neatly trimmed, reflecting his past in espionage."/> </character> </codex> <text> Aurora Carter, with her brilliant green eyes, pushed through the crowd. The Raven's Nest was She was a character of striking contrasts, her wavy chestnut hair casressed her shoulders, her height a couple of inches above the average for a human. She carried herself with a poise that highlighted her athletic prowess. Every table, there was Silas, his greying hair tied back with a strip of leather, running the bar with effortless precision. His hazel eyes, always observading a keen intellect, flickered with a spark of mischief that often led to a smile. She arrived late, much later than Rory had anticipated. The bar was usually filled with laughter and Tonight, however, there was an edge to the mirth, a certain sharpness in Silas' demeanor. Rory didn't know from a background of privilege equips, but from years of living in Dymas, she had learned to navigate it when things went awry. Her eyes scashed into his wine glass at the sight of Silas correcting his own drink. He didn't even notice when she caught open from the back room, holding the pendant up as a shield against the chill of the coming-winter air. Aurora turned to catch the gaze of the patron sitting across from her. She gave a knowing nod, one that spoke of resaping what had been lost and forgotten. She'd learned it was Silas's way, the way of a man who had seen too much, who had lived through the Cold War and come out the other side stronger for it, if not necessarily wiser. "Rory," Silas called out, his voice steady but gentle, "You're late." "I know," she replied, her voice tight, "but you're still in time for the pre-feast meeting." A breeze ruffled the pages of the open book on the counter, stirring the embers in the fireplace. Silas joined more logs to the pile, each one adding a small burst of warmth to the room. The room grew brighter as more patired walked in, the radiant heat from the fire waraning the shadows into sharp relief. Silas reached for a decanter of Scotch whisky from a high shelf, the amber liquid reflecting the dancing flames. He poured the whisky into a snifle glass filled with ice cubes, the cold condensing beautifully against the warm room. Rory accepted the glass with a nod, stepping back to give the Scotch whisky poured over her. She felt the chill of the room, the heat from the whisky making her wish she'd worn more layers. The whisky wararmed her against the chill, its fumes mingling with the scent of the wood and leather. She took a deep breath, steadying herself as she watched Silas pour the whisky into the pendant decanter. She knew it was the smell of the whisky, rich and peaty, that comforted her when she was under stress. It reminded her of the brief moment of unity she had felt with Silas when they were both aware of It was a unity that transcended danger and pain. Aurora blinked as she took in a step deeper into the roomist. She caughted Silas, her eyes meeting his, a question forming. "Silas," she said, "Did you bring the whisky?" He chuckled, a deep rumbling sound coming from his chest. "I did. It's from the Gluttony realm. It's considered a rare delicacy, and it seemed fitting that it should be shared to Aurora's side, given her affethyst traits." The explanation seemed to satisfy the tension, and Aurora felt a rush of relief. She nodded, thanking him for his thoughtfulness, even though her mind was filled with concerny. </text> <violation entry="4412" detail="eyeColor" paragraph="3" substring="brilliant green"> The text says brilliant green eyes, but the codex says bright blue.</violation> <violation entry="4412" detail="age" paragraph="3" substring="24"> The text says 24, but the codex says 25.</violation> <violation entry="4412" detail="hair" paragraph="4" substring="wavy chestnut hair"> The text says wavy chestnut hair, but the codex saysays chestnut hair is straight and shoulder's. </violation> <violation entry="4412' detail="height" paragraph="5" substring="5'7""> The text is says to be 5'7", but the codex says 5'6".5'7" is a canonical height for Aurora, listed in the storype code1 entry. </violation> <violation entry="4412" detail="hairColor" paragraph="4" substring="straight shoulder-length black hair"> The text says straight shoulder-length black hair, but the codex says shoulder-length chestnut brown hair.</violation> <violation entry="8001" detail="species" paragraph="2" substring="Human"> The text says human, but the codex says Human.</violation> <violation entry="8001" detail="eyedward" paragraph="2" substring="hazel"> The text says hazel eyes, but the codex says bright blue.</violation> <violation entry="4412" detail="species" paragraph="6" substring="human"> The text says human, but the codex says Human.</violation> <violation entry="8001" detail="storyRole" paragraph="2" substring="Protagonist"> <violation detail="character's storyRole is "Protagonist", not "Mentor" or any lesser role.</violation> <violations-none/>
created_at
"2026-02-15T19:44:39.030566+00:00"
2/15/2026, 7:44:39 PM
model
"microsoft/wizardlm-2-8x22b"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
516
moderation_latency
(null)
generation_time
30969
tokens_prompt
1444
tokens_completion
1729
native_tokens_prompt
1601
native_tokens_completion
1893
native_tokens_completion_images
(null)
native_tokens_reasoning
0
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.00216628
router
(null)
provider_responses
0
id
"c076d884-a6e8-4001-b0a9-74339a39b2ed"
status
200
is_byok
false
latency
516
endpoint_id
"92d0658f-b48a-4746-96e7-75ea71d5e060"
provider_name
"Novita"
model_permaslug
"microsoft/wizardlm-2-8x22b"
api_type
"completions"
id
"gen-1771184647-h9t1uET9BMCo3g5FTglN"
upstream_id
"c076d884-a6e8-4001-b0a9-74339a39b2ed"
total_cost
0.00216628
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Novita"
Evaluation details
Result
Evaluator
Details
Meta Data
0.0000%
Accuracy (recall)
Matched: 0/5, FP: 0
parsedCount
0
matched
0
total
5
falsePositives
0
expectedDetails
0
expected
entry
"4412"
detail
"eyeColor"
summary
"Aurora has bright blue eyes per her codex entry, but the passage says she has green eyes."
status
"missed"
1
expected
entry
"4412"
detail
"species"
summary
"Aurora is Human per her codex entry, but the passage refers to her as Half-Fae."
status
"missed"
2
expected
entry
"2001"
detail
"chainMaterial"
summary
"The Heartstone Pendant has a silver chain per its codex entry, but the passage says golden chain."
status
"missed"
3
expected
entry
"4413"
detail
"beard"
summary
"Silas's beard matches his grey-streaked auburn hair per codex, but the passage says dark brown beard."
status
"missed"
4
expected
entry
"853"
detail
"ruler"
summary
"Dymas is Prince Belphegor's realm per the codex, but the passage says Prince Mammon's realm."
status
"missed"
falsePositiveDetails
(empty)
0.0000%
Precision
True positives: 0/0
totalReported
0
truePositives
0
reportedDetails
(empty)
10.0000%
Structural validity
Parsed: 0, Well-formed: 0/0
parsedCount
0
wellFormedScore
0
hasAttempt
true
3.3333%