NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHK9ED2NG4F0XSRSNB5QYPKK
Run Details
Model:
GPT-5
Test:
Codex Violation Detection
Scenario:
5 codex entries
Duration:
1m 50s
Cost:
$0.047705
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> </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
<violation entry="4412" detail="eyeColor" paragraph="1" substring="her green eyes">The text says Aurora has green eyes, but the codex lists her eye color as bright blue.</violation> <violation entry="4413" detail="beard" paragraph="2" substring="dark brown beard">The text describes Silas's beard as dark brown, but the codex says it is neatly trimmed and matches his grey-streaked auburn hair.</violation> <violation entry="2001" detail="chainMaterial" paragraph="3" substring="the golden chain">The text says the Heartstone Pendant hangs from a golden chain, but the codex specifies a silver chain.</violation> <violation entry="853" detail="ruler" paragraph="3" substring="Prince Mammon's realm">The text claims Dymas is ruled by Prince Mammon, but the codex states its ruler is Prince Belphegor.</violation> <violation entry="4412" detail="species" paragraph="5" substring="her Half-Fae senses">The text implies Aurora is Half-Fae, but the codex lists her species as Human.</violation> <violation entry="2001" detail="description" paragraph="3" substring="I found something in Dymas.">The text indicates Aurora found the Heartstone Pendant herself, whereas the codex says it was given to her by an unknown benefactor.</violation>
created_at
"2026-02-16T13:17:01.707606+00:00"
2/16/2026, 1:17:01 PM
model
"openai/gpt-5-2025-08-07"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
19331
moderation_latency
(null)
generation_time
71958
tokens_prompt
1441
tokens_completion
1290
native_tokens_prompt
1348
native_tokens_completion
4602
native_tokens_completion_images
0
native_tokens_reasoning
4288
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
"completed"
usage
0.047705
router
(null)
provider_responses
0
id
"resp_02f14bc2e370646a0169931885341081938d88f4cc2ca4a34b"
status
200
is_byok
false
latency
154
endpoint_id
"7c2f859a-7890-4e8e-b1de-1cd1c0a800b4"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5-2025-08-07"
api_type
"completions"
id
"gen-1771247749-8FzN9wPOkAUE6mY2pBZi"
upstream_id
"resp_02f14bc2e370646a0169931885341081938d88f4cc2ca4a34b"
total_cost
0.047705
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
90.0000%
Accuracy (recall)
Matched: 5/5, FP: 1
parsedCount
6
matched
5
total
5
falsePositives
1
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
"matched"
matchedBy
entry
"4412"
detail
"eyeColor"
explanation
"The text says Aurora has green eyes, but the codex lists her eye color as bright blue."
paragraph
1
substring
"her green eyes"
location
extractedText
"her green eyes"
inBounds
true
expectedText
"her green eyes scanning the room"
locationAccurate
true
1
expected
entry
"4412"
detail
"species"
summary
"Aurora is Human per her codex entry, but the passage refers to her as Half-Fae."
status
"matched"
matchedBy
entry
"4412"
detail
"species"
explanation
"The text implies Aurora is Half-Fae, but the codex lists her species as Human."
paragraph
5
substring
"her Half-Fae senses"
location
extractedText
"her Half-Fae senses"
inBounds
true
expectedText
"her Half-Fae senses tingling"
locationAccurate
true
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
"matched"
matchedBy
entry
"2001"
detail
"chainMaterial"
explanation
"The text says the Heartstone Pendant hangs from a golden chain, but the codex specifies a silver chain."
paragraph
3
substring
"the golden chain"
location
extractedText
"the golden chain"
inBounds
true
expectedText
"the golden chain catching the low light"
locationAccurate
true
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
"matched"
matchedBy
entry
"4413"
detail
"beard"
explanation
"The text describes Silas's beard as dark brown, but the codex says 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
"853"
detail
"ruler"
summary
"Dymas is Prince Belphegor's realm per the codex, but the passage says Prince Mammon's realm."
status
"matched"
matchedBy
entry
"853"
detail
"ruler"
explanation
"The text claims Dymas is ruled by Prince Mammon, but the codex states its ruler is Prince Belphegor."
paragraph
3
substring
"Prince Mammon's realm"
location
extractedText
"Prince Mammon's realm"
inBounds
true
expectedText
"Prince Mammon's realm"
locationAccurate
true
falsePositiveDetails
0
parsed
entry
"2001"
detail
"description"
explanation
"The text indicates Aurora found the Heartstone Pendant herself, whereas the codex says it was given to her by an unknown benefactor."
paragraph
3
substring
"I found something in Dymas."
status
"false_positive"
location
extractedText
"I found something in Dymas."
inBounds
true
expectedText
"the golden chain catching the low light"
locationAccurate
false
closestExpected
entry
"2001"
detail
"chainMaterial"
summary
"The Heartstone Pendant has a silver chain per its codex entry, but the passage says golden chain."
reason
"detail mismatch: got \"description\", expected \"chainMaterial\""
83.3333%
Precision
True positives: 5/6
totalReported
6
truePositives
5
reportedDetails
0
parsed
entry
"4412"
detail
"eyeColor"
explanation
"The text says Aurora has green eyes, but the codex lists her eye color as bright blue."
paragraph
1
substring
"her green eyes"
status
"true_positive"
matchedExpected
entry
"4412"
detail
"eyeColor"
summary
"Aurora has bright blue eyes per her codex entry, but the passage says she has green eyes."
location
extractedText
"her green eyes"
inBounds
true
expectedText
"her green eyes scanning the room"
locationAccurate
true
1
parsed
entry
"4413"
detail
"beard"
explanation
"The text describes Silas's beard as dark brown, but the codex says 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 matches his grey-streaked auburn hair per codex, but the passage says dark brown beard."
location
extractedText
"dark brown beard"
inBounds
true
expectedText
"his dark brown beard"
locationAccurate
true
2
parsed
entry
"2001"
detail
"chainMaterial"
explanation
"The text says the Heartstone Pendant hangs from a golden chain, but the codex specifies a silver chain."
paragraph
3
substring
"the golden chain"
status
"true_positive"
matchedExpected
entry
"2001"
detail
"chainMaterial"
summary
"The Heartstone Pendant has a silver chain per its codex entry, but the passage says golden chain."
location
extractedText
"the golden chain"
inBounds
true
expectedText
"the golden chain catching the low light"
locationAccurate
true
3
parsed
entry
"853"
detail
"ruler"
explanation
"The text claims Dymas is ruled by Prince Mammon, but the codex states its ruler is Prince Belphegor."
paragraph
3
substring
"Prince Mammon's realm"
status
"true_positive"
matchedExpected
entry
"853"
detail
"ruler"
summary
"Dymas is Prince Belphegor's realm per the codex, but the passage says Prince Mammon's realm."
location
extractedText
"Prince Mammon's realm"
inBounds
true
expectedText
"Prince Mammon's realm"
locationAccurate
true
4
parsed
entry
"4412"
detail
"species"
explanation
"The text implies Aurora is Half-Fae, but the codex lists her species as Human."
paragraph
5
substring
"her Half-Fae senses"
status
"true_positive"
matchedExpected
entry
"4412"
detail
"species"
summary
"Aurora is Human per her codex entry, but the passage refers to her as Half-Fae."
location
extractedText
"her Half-Fae senses"
inBounds
true
expectedText
"her Half-Fae senses tingling"
locationAccurate
true
5
parsed
entry
"2001"
detail
"description"
explanation
"The text indicates Aurora found the Heartstone Pendant herself, whereas the codex says it was given to her by an unknown benefactor."
paragraph
3
substring
"I found something in Dymas."
status
"false_positive"
location
extractedText
"I found something in Dymas."
inBounds
true
expectedText
"the golden chain catching the low light"
locationAccurate
false
closestExpected
entry
"2001"
detail
"chainMaterial"
summary
"The Heartstone Pendant has a silver chain per its codex entry, but the passage says golden chain."
reason
"detail mismatch: got \"description\", expected \"chainMaterial\""
100.0000%
Structural validity
Parsed: 6, Well-formed: 6/6
parsedCount
6
wellFormedScore
6
91.1111%