NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-06-01KK1HXQBA9EHDAX3EMH41B1AC
Run Details
Model:
GPT-5.4 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
9.8s
Cost:
$0.004485
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
9.61%
Matches word count
(details)
69.61%
Dialogue to Total Word Ratio
(details)
39.6107%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% words of dialogue between two thieves named Molly and Bill who are planning to break into a children's party to steal all the presents. Only include the prose of the scene without any markdown or commentary.
Model response
Messages
Meta
AI
Molly and Bill crouched behind the hedges of Number Twelve, where balloons bobbed like fat, cheerful witnesses and a banner shouted HAPPY EIGHTH, OLIVER! in letters the size of felony charges. From the garden came the shriek of sugar-powered children and the damp thud of a clown losing authority. Bill adjusted his black turtleneck, which in daylight made him look less like a criminal mastermind and more like an unpopular mime. Molly, wearing a cardigan with pockets deep enough for larceny, studied the patio table where the presents sat in a glorious pile of ribboned temptation. “Grab and grin,” Bill whispered. “Grin less,” Molly murmured. A magician in a sequined waistcoat produced a coin from a child’s ear, to riotous applause, while a woman in a paper crown wrestled with a jug of orange squash. Nobody watched the gift table except a sausage dog in a bow tie, and even he seemed morally compromised. Molly checked the route: through the side gate, past the paddling pool, under the banner, seize the loot, out through the alley before the cake was cut and civilization collapsed into icing. Bill inhaled, determined and slightly wheezy. Molly gave him a firm nod. Together they moved with the solemn grace of idiots entering history, toward the mountain of presents and whatever tiny, glittering doom awaited them there.
created_at
"2026-03-06T12:28:25.842Z"
3/6/2026, 12:28:25 PM
model
"openai/gpt-5.4-20260305"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
512
moderation_latency
(null)
generation_time
9713
tokens_prompt
77
tokens_completion
348
native_tokens_prompt
66
native_tokens_completion
288
native_tokens_completion_images
0
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
"completed"
usage
0.004485
router
(null)
provider_responses
0
endpoint_id
"9ff5625c-403f-4d7f-b895-58ac7295062c"
id
"resp_0c99fd3b59b1d2cc0169aac869e5bc8196930a4f8af8f67321"
is_byok
false
latency
197
model_permaslug
"openai/gpt-5.4-20260305"
provider_name
"OpenAI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1772800105-wiSjPUZSHADe3QHkisKt"
upstream_id
"resp_0c99fd3b59b1d2cc0169aac869e5bc8196930a4f8af8f67321"
total_cost
0.004485
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
9.61%
Matches word count
n/a
neededClean
false
words
222
69.61%
Dialogue to Total Word Ratio
Ratio: 2.24%, Deviation: 7.76%
neededClean
false
wordsTotal
223
wordsDialogue
5
39.6107%