NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M36NRMQDS0RZMG3BCHD5BTG0
Run Details
Model:
GPT-6 Luna (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
12.4s
Cost:
$0.000502
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
75.16%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
37.5797%
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
“Children’s parties are the perfect target,” Molly whispered. Bill peered over the hedge. “Because children are small?” “Because adults are distracted by cake.” “Also small, then.” Molly lowered the binoculars. “We go in, collect every present, and vanish before anyone notices.” “Do we have a plan?” “Of course.” “Is it written down?” “No.” “Is it in your head?” “Some of it.” “Which part?” “The part where we get rich.” Bill nodded. “Strong beginning. What’s the middle?” Molly pointed at the garden gate. A hand-painted sign announced: HAPPY BIRTHDAY, ELLIE! Underneath, a cartoon dinosaur wore a party hat and appeared to be regretting it. “We enter as entertainers,” Molly said. “What do we entertain them with?” “Confidence.” “I can juggle.” “You dropped three oranges at the bank.” “They were slippery.” “They were oranges, Bill.” From inside came a burst of laughter, then the unmistakable sound of a grown-up leading children in a song. Bill winced. “Could we wait until they’re all singing?” he asked. “Why?” “So no one hears us.” “They’re singing about a fish.” “Fish songs are loud.” Molly studied the gate. “We’ll say we’re delivering a present.” “What present?” “An imaginary one.” “Won’t they ask to see it?” “Children believe in imaginary things.” “Not parcels, Molly.” A small voice called from the garden, “Are you the magicians?” Molly and Bill froze. A girl in a paper crown had appeared beside the gate, holding a cupcake with a single candle. Bill whispered, “Tell her we’re magicians.” Molly whispered back, “You can’t even make a coin disappear.” “I can make it disappear into my sleeve.” “That’s where you keep your sandwiches.” The girl tilted her head. “Are you here for Ellie’s party?” “Absolutely,” Molly said, putting on her brightest smile. “We’re the—” “Cake inspectors,” Bill blurted. Molly looked at him. “What?” he whispered. “It’s a respectable profession.” The girl considered this. “The cake inspector already came. He ate two slices.” “Thorough,” Bill said. Molly crouched. “We’re actually here to give Ellie a very special surprise.” “What is it?” “A lesson in generosity,” Molly said. Bill blinked. “Is that what we’re calling it?” “Today, yes.” The girl opened the gate. “You can come in, but you have to wear party hats.” Molly glanced at Bill. “We’re not staying.” “Of course not,” Bill said. “We’re merely entering a children’s party wearing hats, apparently.” The girl handed them two paper crowns. Bill’s had a glittery unicorn on it. “I look ridiculous,” he murmured. “You look trustworthy,” Molly replied. They stepped into the garden. Ellie, surrounded by balloons and relatives, waved them over. “Are you the surprise?” she asked. Molly looked at the piled presents, then at the children watching expectantly. “Yes,” she said. “We’re the people who help carry gifts to the table.” Bill leaned close. “That’s not stealing.” “Not yet,” Molly whispered. He lifted a present, read the tag, and carried it carefully to Ellie. “Happy birthday,” he said. Ellie beamed. “Thank you!” Molly picked up another. Bill glanced at her. “We’re going to need a new plan.” “After cake,” Molly said. “Cake inspection?” “Strictly professional.”
created_at
"2026-09-23T08:22:54.964Z"
9/23/2026, 8:22:54 AM
model
"openai/gpt-6-luna-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4269
moderation_latency
(null)
generation_time
12428
tokens_prompt
75
tokens_completion
965
native_tokens_prompt
66
native_tokens_completion
990
native_tokens_completion_images
0
native_tokens_reasoning
229
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
0.0005016
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790151774-KXKZojrY092RVkI1ObM2"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790151774-fbSqoYfrhu3ZIo9qzvNu"
upstream_id
"resp_082f5503bfe15ece016ab38c5f0bcc87d1a11267a2bc84c473"
provider_responses
0
endpoint_id
"05e94e02-b9c2-4bbb-ba55-4082ee9ad687"
id
"resp_082f5503bfe15ece016ab38c5f0bcc87d1a11267a2bc84c473"
is_byok
false
latency
463
model_permaslug
"openai/gpt-6-luna-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.0005016
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
75.16%
Matches word count
n/a
neededClean
false
words
513
0.00%
Dialogue to Total Word Ratio
Ratio: 55.73%, Deviation: 14.27%
neededClean
false
wordsTotal
515
wordsDialogue
287
37.5797%