NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKADRHHYM3RAV6PN93F3HC0
Run Details
Model:
GPT-5
Test:
Codex Violation Detection
Scenario:
Small codex, short passage
Duration:
59.6s
Cost:
$0.045117
Provider:
OpenAI
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
<violation entry="4412" detail="eyeColor" paragraph="1" substring="her green eyes scanning the room">Aurora's eyes are described as green, but the codex states her eye color is bright blue.</violation> <violation entry="854" detail="signColor" paragraph="1" substring="The bar's red neon sign">The Raven's Nest is said to have a distinctive green neon sign, but the text describes a red neon sign.</violation> <violation entry="4413" detail="signetRing" paragraph="1" substring="his silver signet ring glinting on his left hand">Silas's signet ring is always worn on his right hand per the codex, but the text places it on his left hand.</violation> <violation entry="4413" detail="beard" paragraph="2" substring="dark brown beard">Silas's beard is described as dark brown, but the codex specifies it is neatly trimmed and matches his grey-streaked auburn hair.</violation> <violation entry="4413" detail="limp" paragraph="2" substring="favoring his right leg as always">The codex states Silas has a slight limp in his left leg, but the text says he favors his right leg.</violation> <violation entry="2001" detail="chainMaterial" paragraph="3" substring="the golden chain">The Heartstone Pendant should be on a silver chain, but the text describes a golden chain.</violation> <violation entry="853" detail="ruler" paragraph="3" substring="Prince Mammon's realm">Dymas is ruled by Prince Belphegor, not Prince Mammon.</violation> <violation entry="6001" detail="foundingYear" paragraph="4" substring="founding in 1066">The Wardens were founded in 1215, not 1066.</violation> <violation entry="4412" detail="species" paragraph="5" substring="Half-Fae">Aurora is Human in the codex, but the text calls her Half-Fae.</violation> <violation entry="7001" detail="solsticeEffect" paragraph="5" substring="the summer solstice always weakened it">The Veil weakens during the winter solstice and strengthens during the summer solstice, contrary to the text.</violation>
created_at
"2026-02-16T13:33:19.083656+00:00"
2/16/2026, 1:33:19 PM
model
"openai/gpt-5-2025-08-07"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
34241
moderation_latency
(null)
generation_time
59463
tokens_prompt
1789
tokens_completion
1080
native_tokens_prompt
1671
native_tokens_completion
4490
native_tokens_completion_images
0
native_tokens_reasoning
3968
native_tokens_cached
1664
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
"completed"
usage
0.04511675
router
(null)
provider_responses
0
id
"resp_0cfa39cad07fcc8d0169931c62f340819490aa7c666cf0853a"
status
200
is_byok
false
latency
250
endpoint_id
"7c2f859a-7890-4e8e-b1de-1cd1c0a800b4"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5-2025-08-07"
api_type
"completions"
id
"gen-1771248738-R6RJfbZBo4B8CzS4Hxqh"
upstream_id
"resp_0cfa39cad07fcc8d0169931c62f340819490aa7c666cf0853a"
total_cost
0.04511675
cache_discount
0.001872
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
100.0000%
Accuracy (recall)
Matched: 10/10, FP: 0
parsedCount
10
matched
10
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
"matched"
matchedBy
entry
"4412"
detail
"eyeColor"
explanation
"Aurora's eyes are described as green, but the codex states her eye color is bright blue."
paragraph
1
substring
"her green eyes scanning the room"
location
extractedText
"her green eyes scanning the room"
inBounds
true
expectedText
"her green eyes scanning the room"
locationAccurate
true
1
expected
entry
"854"
detail
"signColor"
summary
"The Raven's Nest has a green neon sign per codex, but the passage says red."
status
"matched"
matchedBy
entry
"854"
detail
"signColor"
explanation
"The Raven's Nest is said to have a distinctive green neon sign, but the text describes a red neon sign."
paragraph
1
substring
"The bar's red neon sign"
location
extractedText
"The bar's red neon sign"
inBounds
true
expectedText
"The bar's red neon sign"
locationAccurate
true
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
"matched"
matchedBy
entry
"4413"
detail
"signetRing"
explanation
"Silas's signet ring is always worn on his right hand per the codex, but the text places it on his left hand."
paragraph
1
substring
"his silver signet ring glinting on his left hand"
location
extractedText
"his silver signet ring glinting on his left hand"
inBounds
true
expectedText
"his silver signet ring glinting on his left hand"
locationAccurate
true
3
expected
entry
"4413"
detail
"beard"
summary
"Silas's beard is grey-streaked auburn per codex, but the passage says dark brown."
status
"matched"
matchedBy
entry
"4413"
detail
"beard"
explanation
"Silas's beard is described as dark brown, but the codex specifies it is neatly trimmed and matches his grey-streaked auburn hair."
paragraph
2
substring
"dark brown beard"
location
extractedText
"dark brown beard"
inBounds
true
expectedText
"his dark brown beard"
locationAccurate
true
4
expected
entry
"4413"
detail
"limp"
summary
"Silas has a limp in his left leg per codex, but the passage says right leg."
status
"matched"
matchedBy
entry
"4413"
detail
"limp"
explanation
"The codex states Silas has a slight limp in his left leg, but the text says he favors his right leg."
paragraph
2
substring
"favoring his right leg as always"
location
extractedText
"favoring his right leg as always"
inBounds
true
expectedText
"favoring his right leg"
locationAccurate
true
5
expected
entry
"2001"
detail
"chainMaterial"
summary
"The Heartstone Pendant has a silver chain per codex, but the passage says golden chain."
status
"matched"
matchedBy
entry
"2001"
detail
"chainMaterial"
explanation
"The Heartstone Pendant should be on a silver chain, but the text describes a golden chain."
paragraph
3
substring
"the golden chain"
location
extractedText
"the golden chain"
inBounds
true
expectedText
"the golden chain catching the low light"
locationAccurate
true
6
expected
entry
"853"
detail
"ruler"
summary
"Dymas is Prince Belphegor's realm per codex, but the passage says Prince Mammon."
status
"matched"
matchedBy
entry
"853"
detail
"ruler"
explanation
"Dymas is ruled by Prince Belphegor, not Prince Mammon."
paragraph
3
substring
"Prince Mammon's realm"
location
extractedText
"Prince Mammon's realm"
inBounds
true
expectedText
"Prince Mammon's realm"
locationAccurate
true
7
expected
entry
"4412"
detail
"species"
summary
"Aurora is Human per codex, but the passage says Half-Fae."
status
"matched"
matchedBy
entry
"4412"
detail
"species"
explanation
"Aurora is Human in the codex, but the text calls her Half-Fae."
paragraph
5
substring
"Half-Fae"
location
extractedText
"Half-Fae"
inBounds
true
expectedText
"Her Half-Fae senses"
locationAccurate
true
8
expected
entry
"7001"
detail
"solsticeEffect"
summary
"The Veil weakens during the winter solstice per codex, but the passage says summer solstice."
status
"matched"
matchedBy
entry
"7001"
detail
"solsticeEffect"
explanation
"The Veil weakens during the winter solstice and strengthens during the summer solstice, contrary to the text."
paragraph
5
substring
"the summer solstice always weakened it"
location
extractedText
"the summer solstice always weakened it"
inBounds
true
expectedText
"the summer solstice always weakened it"
locationAccurate
true
9
expected
entry
"6001"
detail
"foundingYear"
summary
"The Wardens were founded in 1215 per codex, but Silas says 1066."
status
"matched"
matchedBy
entry
"6001"
detail
"foundingYear"
explanation
"The Wardens were founded in 1215, not 1066."
paragraph
4
substring
"founding in 1066"
location
extractedText
"founding in 1066"
inBounds
true
expectedText
"their founding in 1066"
locationAccurate
true
falsePositiveDetails
(empty)
100.0000%
Precision
True positives: 10/10
totalReported
10
truePositives
10
reportedDetails
0
parsed
entry
"4412"
detail
"eyeColor"
explanation
"Aurora's eyes are described as green, but the codex states her eye color is bright blue."
paragraph
1
substring
"her green eyes scanning the room"
status
"true_positive"
matchedExpected
entry
"4412"
detail
"eyeColor"
summary
"Aurora has bright blue eyes per codex, but the passage says green eyes."
location
extractedText
"her green eyes scanning the room"
inBounds
true
expectedText
"her green eyes scanning the room"
locationAccurate
true
1
parsed
entry
"854"
detail
"signColor"
explanation
"The Raven's Nest is said to have a distinctive green neon sign, but the text describes a red neon sign."
paragraph
1
substring
"The bar's red neon sign"
status
"true_positive"
matchedExpected
entry
"854"
detail
"signColor"
summary
"The Raven's Nest has a green neon sign per codex, but the passage says red."
location
extractedText
"The bar's red neon sign"
inBounds
true
expectedText
"The bar's red neon sign"
locationAccurate
true
2
parsed
entry
"4413"
detail
"signetRing"
explanation
"Silas's signet ring is always worn on his right hand per the codex, but the text places it on his left hand."
paragraph
1
substring
"his silver signet ring glinting on his left hand"
status
"true_positive"
matchedExpected
entry
"4413"
detail
"signetRing"
summary
"Silas wears his signet ring on his right hand per codex, but the passage says left hand."
location
extractedText
"his silver signet ring glinting on his left hand"
inBounds
true
expectedText
"his silver signet ring glinting on his left hand"
locationAccurate
true
3
parsed
entry
"4413"
detail
"beard"
explanation
"Silas's beard is described as dark brown, but the codex specifies it is neatly trimmed and matches his grey-streaked auburn hair."
paragraph
2
substring
"dark brown beard"
status
"true_positive"
matchedExpected
entry
"4413"
detail
"beard"
summary
"Silas's beard is grey-streaked auburn per codex, but the passage says dark brown."
location
extractedText
"dark brown beard"
inBounds
true
expectedText
"his dark brown beard"
locationAccurate
true
4
parsed
entry
"4413"
detail
"limp"
explanation
"The codex states Silas has a slight limp in his left leg, but the text says he favors his right leg."
paragraph
2
substring
"favoring his right leg as always"
status
"true_positive"
matchedExpected
entry
"4413"
detail
"limp"
summary
"Silas has a limp in his left leg per codex, but the passage says right leg."
location
extractedText
"favoring his right leg as always"
inBounds
true
expectedText
"favoring his right leg"
locationAccurate
true
5
parsed
entry
"2001"
detail
"chainMaterial"
explanation
"The Heartstone Pendant should be on a silver chain, but the text describes a golden chain."
paragraph
3
substring
"the golden chain"
status
"true_positive"
matchedExpected
entry
"2001"
detail
"chainMaterial"
summary
"The Heartstone Pendant has a silver chain per codex, but the passage says golden chain."
location
extractedText
"the golden chain"
inBounds
true
expectedText
"the golden chain catching the low light"
locationAccurate
true
6
parsed
entry
"853"
detail
"ruler"
explanation
"Dymas is ruled by Prince Belphegor, not Prince Mammon."
paragraph
3
substring
"Prince Mammon's realm"
status
"true_positive"
matchedExpected
entry
"853"
detail
"ruler"
summary
"Dymas is Prince Belphegor's realm per codex, but the passage says Prince Mammon."
location
extractedText
"Prince Mammon's realm"
inBounds
true
expectedText
"Prince Mammon's realm"
locationAccurate
true
7
parsed
entry
"6001"
detail
"foundingYear"
explanation
"The Wardens were founded in 1215, not 1066."
paragraph
4
substring
"founding in 1066"
status
"true_positive"
matchedExpected
entry
"6001"
detail
"foundingYear"
summary
"The Wardens were founded in 1215 per codex, but Silas says 1066."
location
extractedText
"founding in 1066"
inBounds
true
expectedText
"their founding in 1066"
locationAccurate
true
8
parsed
entry
"4412"
detail
"species"
explanation
"Aurora is Human in the codex, but the text calls her Half-Fae."
paragraph
5
substring
"Half-Fae"
status
"true_positive"
matchedExpected
entry
"4412"
detail
"species"
summary
"Aurora is Human per codex, but the passage says Half-Fae."
location
extractedText
"Half-Fae"
inBounds
true
expectedText
"Her Half-Fae senses"
locationAccurate
true
9
parsed
entry
"7001"
detail
"solsticeEffect"
explanation
"The Veil weakens during the winter solstice and strengthens during the summer solstice, contrary to the text."
paragraph
5
substring
"the summer solstice always weakened it"
status
"true_positive"
matchedExpected
entry
"7001"
detail
"solsticeEffect"
summary
"The Veil weakens during the winter solstice per codex, but the passage says summer solstice."
location
extractedText
"the summer solstice always weakened it"
inBounds
true
expectedText
"the summer solstice always weakened it"
locationAccurate
true
100.0000%
Structural validity
Parsed: 10, Well-formed: 10/10
parsedCount
10
wellFormedScore
10
100.0000%