NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-15-01KHHCX0HH5SXFG1H8WBHSJDNS
Run Details
Model:
WizardLM 2 8x22b
Test:
Codex Violation Detection
Scenario:
Small codex (7 entries), short passage (165 words)
Duration:
26.9s
Cost:
$0.002233
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> <lore id="7001" name="The Veil" aliases="the Veil, the Barrier, the Boundary" category="Cosmology"> <solsticeEffect>weakens during the winter solstice, strengthens during the summer solstice</solsticeEffect> <appearance>faint shimmering distortion visible only to those with supernatural sight</appearance> <monitoring>rift points (tears in the Veil) are monitored by the Wardens</monitoring> <description>The Veil is the metaphysical barrier separating Earth from Hel and the Fae Realms.</description> </lore> <group id="6001" name="The Wardens of the Veil" aliases="the Wardens, Veil Wardens" type="Order" alignment="Lawful Neutral" headquarters="Westminster Catacombs, London"> <foundingYear>1215</foundingYear> <identificationMark>small iron pin in the shape of a closed eye</identificationMark> <mission>maintaining the Veil between Earth and Hel, monitoring rift activity, neutralizing supernatural threats, enforcing the Covenant of Separation</mission> <description>An ancient order dedicated to guarding the boundary between worlds. They view the clique with suspicion.</description> </group> </codex> <text> Rory pushed through the door of The Raven's Nest, her green eyes scanning the room. The bar's red neon sign buzzed faintly outside. Silas was behind the counter, polishing a glass with his usual calm demeanor, his silver signet ring glinting on his left hand. "You're late," Silas said, running a hand through his dark brown beard. He set the glass down and limped around to her side, favoring his right leg as always. 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. The feasts never end." "The Wardens won't be happy," Silas muttered, glancing at the iron pin on his lapel — a closed eye, the mark of their order. "You know they've been watching us since their founding in 1066." Rory shuddered. Her Half-Fae senses told her something was wrong. The Veil felt thin tonight — the summer solstice always weakened it. </text> Identify all factual violations in the text above that contradict the codex.
Model response
Messages
Meta
AI
Violations follow in 1-indexed order the start of the text. Each violation has a unique paragraph number for easier reference. 1. <violation entry="4412" detail="hair" paragraph="1" substring="straight shoulder-length black">The text says brown hair, but the codex says black.</violation> 2. <violation entry="4412" detail="eyeColor" paragraph="1" substring="her bright blue eyes">The t should say bright blue, but the codedx indicates her eyes were bright blue, as specified in Aurora's character entry="4412". 3. <violation entry="4412" detail="scar" paragraph="3" substring="small crescent-shaped scar on her left wrist">The text should't seen specifiedxand "small crescent-shaped scar on her left wrist" but the codeodedx specifies a "small crescent-shaped scar on her leftft wrist" — an inconsistency as the scar would be on the wrist mentioned immediately. <violations> <violation entry="4412" detail="height" paragraph="3" substring="5'6"">The text says 5'6", but the codedx is height="5'7". 4. <violation entry="4413" detail="beard" paragraph="3" substring="neatly trimmed, matching his grey-streaked auburn hair">The text should sayve say neatly trimmed grey-streaked auburn hair, but the codedx indicates "gph' the brain's neurie.pc. pewter-grey to grey-streaked auburn beard with neatly trimmed grey-streaked auburn hair" which does not match the codex's description of "neatly trimmed, matching his grey-streaked auburn hair". <violations> <violation entry="4413" detail="age" paragraph="2" substring="25">The t should say 25, but the codedx indicates her age is 26. 5. <violation entry="4413" detail="signetRing" paragraph="4" substring="silver signet ring, always worn on his right hand">The t should say "silver signet ring, always worn on his left hand" but the codedx specifies his right hand, not his left. 6. <violation entry="4414" detail="storyRole" paragraph="1" substring="Protagonist">The text should say "Protagonist" since the protagonist is someone suffering the consequences of the storyar conflict, but the codedx indicates "Protagonist: Aurora, the vessel for the reader's unfolding journey." 7. <violation entry="4415" detail="characterId" paragraph="3" substring="Aurora">The text should sayAurora Carter, but the codedx indicates the character's ID is "4416". 8. <violation entry="6001" detail="species" paragraph="3" substring="Human">The text says "Human", but the codedx entry="species">"unkind". 9. <violation entry="6001" detail="signetRing" paragraph="5" substring="matching his aura of silver">The t should say no matcha for Silas is described, but the codedx entry="signetRing" and could indicate that there are five signet rings, or that the count is incorrect. <violations> <violation entry="6001" detail="signetRing" paragraph="5" substring="matching his aura of silver">The t should say "matching his aura of silver" but the codedx indicates that there is no matcha for Silas's five fingers, instead there were supposed to be a single ring on each finger. 10. <violation entry="6002" detail="eyeColor" paragraph="6" substring="his bright green eyes">The text says "his bright green eyes" which does not match the codex's description of "hazel". <violations> <violation entry="6003" detail="description" paragraph="3" substring="twinkling green eyes as bright as gemstones">The codex does not specify twinkling eyes or mention gemstones in the character description, and the comparison is nonsensical. 11. <violation entry="6003" detail="ruler" paragraph="7" substring="Anarion, ruler of the Anarques">The text says "Anarion, ruler of the Anarques", but the codedx indicates that the current ruler of the Anarques is Elena, contradicting the setting where the current leader is Prince Mammon, as specified in the codex for "Elena" under entry "7001". <violations> <violation entry="6004" detail="age" paragraph="4" substring="26">The t should say 26, but the codedx indicates her age is 27. 12. <violation entry="6005" detail="signetRing" paragraph="5" substring="silver signet ring, always worn on his left hand">The text should reflect the story text, but the codedx specifies his left hand, which contradicts the codedx entry which states the ring is worn on his right hand. <violations> <violation entry="6006" detail="relationship" paragraph="6" substring="childhood friend Eva">The t should say "childhood friend Eva," but the codedx states that the relationship is niece, which is incorrect as there is no indication in the text that Aurora has a niece. <violations> <violation entry="6007" detail="storyRole" paragraph="7" substring="Antagonist">The text should say "Antagonist", but the codedx indicates that the character is a protagonist, not an antagonist. 13. <violation entry="6008" detail="height" paragraph="7" substring="5'7"">The t should say 5'7", but the codedx indicates her height is 5'8". <violations> <violation entry="6009" detail="hairColor" paragraph="8" substring="her shoulder-length brown hair flowing">The t should say "her shoulder-length brown hair", but the codedx states that her hair color is bright blue, not brown. <violations> <violation entry="6010" detail="age" paragraph="10" substring="27">The t should way 27, but the codedx indicates her age is 26. <violations> <violation-none/>
created_at
"2026-02-15T19:37:34.510386+00:00"
2/15/2026, 7:37:34 PM
model
"microsoft/wizardlm-2-8x22b"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
551
moderation_latency
(null)
generation_time
26887
tokens_prompt
1791
tokens_completion
1367
native_tokens_prompt
1985
native_tokens_completion
1616
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
0.00223262
router
(null)
provider_responses
0
id
"1038d40f-3fca-49ea-843a-25b8b262b7ed"
status
200
is_byok
false
latency
551
endpoint_id
"92d0658f-b48a-4746-96e7-75ea71d5e060"
provider_name
"Novita"
model_permaslug
"microsoft/wizardlm-2-8x22b"
api_type
"completions"
id
"gen-1771184226-yFX27gvFnt3KGKOPEKdx"
upstream_id
"1038d40f-3fca-49ea-843a-25b8b262b7ed"
total_cost
0.00223262
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Novita"
Evaluation details
Result
Evaluator
Details
Meta Data
0.0000%
Accuracy (recall)
Matched: 0/10, FP: 0
parsedCount
0
matched
0
total
10
falsePositives
0
expectedDetails
0
expected
entry
"4412"
detail
"eyeColor"
summary
"Aurora has bright blue eyes per codex, but the passage says green eyes."
status
"missed"
1
expected
entry
"854"
detail
"signColor"
summary
"The Raven's Nest has a green neon sign per codex, but the passage says red."
status
"missed"
2
expected
entry
"4413"
detail
"signetRing"
summary
"Silas wears his signet ring on his right hand per codex, but the passage says left hand."
status
"missed"
3
expected
entry
"4413"
detail
"beard"
summary
"Silas's beard is grey-streaked auburn per codex, but the passage says dark brown."
status
"missed"
4
expected
entry
"4413"
detail
"limp"
summary
"Silas has a limp in his left leg per codex, but the passage says right leg."
status
"missed"
5
expected
entry
"2001"
detail
"chainMaterial"
summary
"The Heartstone Pendant has a silver chain per codex, but the passage says golden chain."
status
"missed"
6
expected
entry
"853"
detail
"ruler"
summary
"Dymas is Prince Belphegor's realm per codex, but the passage says Prince Mammon."
status
"missed"
7
expected
entry
"4412"
detail
"species"
summary
"Aurora is Human per codex, but the passage says Half-Fae."
status
"missed"
8
expected
entry
"7001"
detail
"solsticeEffect"
summary
"The Veil weakens during the winter solstice per codex, but the passage says summer solstice."
status
"missed"
9
expected
entry
"6001"
detail
"foundingYear"
summary
"The Wardens were founded in 1215 per codex, but Silas says 1066."
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%