NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M37HAEYZG2B7TRCAVFS8SVK2
Run Details
Model:
GPT-6 Sol (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
17.7s
Cost:
$0.008472
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
0.03%
Matches word count
(details)
57.38%
Dialogue to Total Word Ratio
(details)
28.7028%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 70% 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
The community hall glittered across the street. Through its windows, Molly could see balloons, a chocolate fountain, and twenty-three wrapped presents piled beneath a banner that read HAPPY BIRTHDAY, BEA! Beside her, Bill adjusted the enormous papier-mâché horse head tucked under his arm. “We go in at four,” Molly said. “Why four?” “That’s when they bring out the cake. Everyone will be distracted.” “Except Bea.” “Why Bea?” “She’s seven. Seven-year-olds notice everything. I once tried to hide a pea under my mashed potatoes. My niece found it from another room.” Molly studied the hall. “Then we need disguises.” “I have the horse.” “That’s one disguise for two people.” “We could both fit inside it.” “That’s a head, Bill. There’s no horse behind it.” “There will be if you put on the brown coat.” “I’m not being your horse’s backside.” “Fine. I’ll be the magician, you be my assistant.” “You don’t know any tricks.” “I can make twenty-three presents disappear.” “That’s the crime, not a trick.” Bill peered through the window. “What if we say we’re collecting donations?” “From a birthday party?” “Children are famously generous.” “With their own presents?” “Perhaps not immediately.” A woman inside the hall set a second cake on the table. It wore a tiny marzipan crown. “Right,” Molly said. “We join the party, locate the gifts, and slip out through the kitchen.” “The kitchen door has an alarm.” “How do you know?” “I helped install it.” “You said you’d never been here.” “I haven’t been here as a criminal.” Molly pinched the bridge of her nose. “What kind of alarm?” “A loud one. Very reliable. I’m proud of it.” “Then we use the front door.” “With twenty-three presents?” “We’ll need a cart.” “There’s a cart beside the cake.” “That’s for the cake.” “Once they’ve eaten it, the cart will be free.” “And why would two strangers wheel a tower of presents out the front door?” Bill lifted the horse head. “Because the birthday horse is taking them to the royal stables.” “Don’t say that to anyone.” “You’re right. Too many questions about the stables.” Inside, a little girl pressed her face to the window. She waved at the horse head. Bill waved back with its painted hoof. “She’s seen us,” Molly whispered. “Maybe she thinks we’re entertainment.” “That makes us more conspicuous.” “She’s coming outside.” The hall door opened. Bea stepped out wearing a paper crown and the solemn expression of someone hiring staff. “Are you the pony?” she asked. Bill glanced at Molly. “I could be.” “Good. Mum said no pony because of the carpet, but you can stay outside. You’re late.” “We haven’t agreed to—” Molly began. Bea handed her a fistful of ribbons. “These go on the pony. After cake, everyone gets a ride.” Bill lowered the horse head over his face. His voice came out muffled. “How many rides?” “Twenty-three,” Bea said. “I counted.” Molly watched Bea skip back inside, then tied a ribbon around Bill’s neck. “We can still leave,” he said. “Not before the rides.” “You’re abandoning the plan?” “I’m revising it. We came to steal all the presents. We’re leaving with twenty-three party bags.” “And sore knees,” Bill said.
created_at
"2026-09-23T16:24:30.63Z"
9/23/2026, 4:24:30 PM
model
"openai/gpt-6-sol-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
5186
moderation_latency
(null)
generation_time
17367
tokens_prompt
75
tokens_completion
937
native_tokens_prompt
66
native_tokens_completion
834
native_tokens_completion_images
0
native_tokens_reasoning
99
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"completed"
service_tier
"default"
usage
0.008472
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790180670-UqNfeEo60fxHwWNEnz4I"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790180670-KQbUMB0UDvVSRTfK3DMv"
upstream_id
"resp_0da6a2ddfc7c27c0016ab3fd3edd6487d1917ab51cc422feb4"
provider_responses
0
endpoint_id
"1cfc7d9d-4404-4b8e-9ee4-58ae45c9dcd4"
id
"resp_0da6a2ddfc7c27c0016ab3fd3edd6487d1917ab51cc422feb4"
is_byok
false
latency
1067
model_permaslug
"openai/gpt-6-sol-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.008472
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
0.03%
Matches word count
n/a
neededClean
false
words
530
57.38%
Dialogue to Total Word Ratio
Ratio: 66.67%, Deviation: 3.33%
neededClean
false
wordsTotal
537
wordsDialogue
358
28.7028%