NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-06-01KK1HT4552DGVM8KW1TC539JY
Run Details
Model:
GPT-5.4 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
8.9s
Cost:
$0.004350
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
93.65%
Matches word count
(details)
94.89%
Dialogue to Total Word Ratio
(details)
94.2675%
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 hedge outside Number Twelve, where balloons bobbed like overeager sentries and a papier-mâché dragon guarded the gate with the vacant confidence of school craft. Inside, sugar-drunk children ricocheted through the garden while adults laughed the desperate laugh of people trapped beside a hired magician. On the patio sat the treasure: a mountain of bright presents, glinting under a banner that read HAPPY 7TH BIRTHDAY, OLIVER, as if naming the victim made the crime ruder. Bill adjusted his flat cap and peered through the leaves. “We go in smiling.” Molly checked the timing on her watch, then the size of the cake, then Bill, in that order. “You never smile naturally. You look taxidermied.” A clown on stilts wandered past the gate, folding balloons into improbable dogs and one extremely convincing ferret. Molly’s eyes narrowed with professional admiration. The plan had seemed elegant in the van: Bill would distract the parents by pretending to be the entertainment, while Molly liberated the presents into a sack labeled MINI GOLF SUPPLIES. Elegant plans, she knew, usually ended with somebody in custard. Bill straightened, breathed deeply, and stepped toward the gate just as the magician inside shouted for a volunteer and every child turned, hungry for chaos.
created_at
"2026-03-06T12:26:27.884Z"
3/6/2026, 12:26:27 PM
model
"openai/gpt-5.4-20260305"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
413
moderation_latency
(null)
generation_time
8851
tokens_prompt
77
tokens_completion
343
native_tokens_prompt
66
native_tokens_completion
279
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
0.00435
router
(null)
provider_responses
0
endpoint_id
"9ff5625c-403f-4d7f-b895-58ac7295062c"
id
"resp_07bb6e6c29d702790169aac7f3f1208197b9ddc5fe7af38548"
is_byok
false
latency
136
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-1772799987-mS5MZXs8FUQu4jUc95zL"
upstream_id
"resp_07bb6e6c29d702790169aac7f3f1208197b9ddc5fe7af38548"
total_cost
0.00435
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
93.65%
Matches word count
n/a
neededClean
false
words
209
94.89%
Dialogue to Total Word Ratio
Ratio: 5.21%, Deviation: 4.79%
neededClean
false
wordsTotal
211
wordsDialogue
11
94.2675%