NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M37HDRE8J9DJE1FDK6E7T6FF
Run Details
Model:
GPT-6 Sol
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
23.3s
Cost:
$0.007262
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
63.69%
Dialogue to Total Word Ratio
(details)
81.1998%
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
Molly spread a crayon drawing across the café table. It showed a house, a cake, and a dinosaur wearing a crown. “Is that the floor plan?” Bill asked. “It’s the invitation.” “Why is the dinosaur in charge?” “The party has a theme.” Bill leaned closer. “That dinosaur looks familiar.” Molly tapped the paper. “Birthday child: Daisy. Location: number fourteen. Time: two o’clock. Mission: all the presents.” “Daisy’s turning six,” Bill said. “Six-year-olds receive presents.” “They also remember faces.” “Which is why we wear disguises.” Molly set two paper hats on the table. One read PARTY ANIMAL. The other read BIRTHDAY GIRL. “I’m not wearing that,” Bill said. “You can have the animal one.” “Who gave you these?” “I bought them.” “At a shop?” “At a party shop. Keep up.” Bill picked up the birthday hat. “You’re planning to walk into a stranger’s house wearing this?” “No. You are.” “I’ll be recognized as an imposter the moment Daisy sees me.” “Then we swap hats.” Molly reached for the birthday hat. Bill held it away from her. “I have a better question,” he said. “How do we leave carrying every present?” “Large sack.” “What sort of sack?” “The sort that holds presents.” “And when someone asks why two adults are loading birthday gifts into a sack?” “We say we’re helping.” “With what?” “Tidying.” “During the party?” “Children make a mess.” A waiter arrived with two coffees and glanced at the drawing. “Cute dinosaur.” “It’s evidence,” Bill said. “It’s a birthday invitation,” Molly said. The waiter backed away. Bill lowered his voice. “We cannot steal from children.” “You said that about the school raffle.” “Because the prize was a pony.” “We didn’t steal the pony.” “We stole the raffle tickets.” “And won a blender.” “Which you gave to your mother.” “She makes excellent soup.” “That is beside the point. These are Daisy’s presents.” Molly looked at the invitation. She had found it tucked beneath her door that morning, along with a note in the same purple crayon. “It’s from my niece,” she said. “Daisy is your niece?” “Apparently. My sister says I never come to family things, so Daisy invited me herself.” Bill stared at her. “You made a plan to rob your niece?” “I saw the gift table and panicked.” “Why?” “Because I haven’t bought her anything.” Bill turned the invitation over. “There’s a note.” “I know.” He read aloud. “‘Aunt Molly, please come. You can bring your friend Bill. I made enough hats.’” He looked up. “She made hats for us.” Molly took back the birthday hat. Inside, in purple crayon, was written AUNT MOLLY. Bill smiled. “I think we should go.” “Without a present?” “We’ll buy one on the way.” “With what money?” Bill slid the raffle blender’s receipt across the table. “Your mother returned it.” Molly blinked. “She hates my gifts.” “She asked me to take you shopping.” “Traitor.” “At least I didn’t propose stealing from Daisy.” Molly folded the invitation carefully. “Fine. We’ll buy a dinosaur.” “And wear the hats?” “Obviously. We’re not monsters.”
created_at
"2026-09-23T16:26:18.448Z"
9/23/2026, 4:26:18 PM
model
"openai/gpt-6-sol-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2665
moderation_latency
(null)
generation_time
23269
tokens_prompt
75
tokens_completion
916
native_tokens_prompt
66
native_tokens_completion
713
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)
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
0.007262
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790180778-ag1rD83jAAQpc6EiwNgQ"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790180778-WfjKlD9G3QEAGkwwR70i"
upstream_id
"resp_03a28baae2f7a33a016ab3fdaa8e4087d1af813decf2ed238d"
provider_responses
0
endpoint_id
"1cfc7d9d-4404-4b8e-9ee4-58ae45c9dcd4"
id
"resp_03a28baae2f7a33a016ab3fdaa8e4087d1af813decf2ed238d"
is_byok
false
latency
993
model_permaslug
"openai/gpt-6-sol-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.007262
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
98.71%
Matches word count
n/a
neededClean
false
words
506
63.69%
Dialogue to Total Word Ratio
Ratio: 67.00%, Deviation: 3.00%
neededClean
false
wordsTotal
506
wordsDialogue
339
81.1998%