NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M36NMM0M4GKNK0RXHFEVMNX5
Run Details
Model:
GPT-6 Luna (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
13.7s
Cost:
$0.000617
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
6.09%
Matches word count
(details)
0.11%
Dialogue to Total Word Ratio
(details)
3.1024%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 50% 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 crouched behind a shrub shaped like a lopsided dinosaur, studying the house across the street. Paper streamers fluttered from its windows. A banner announced HAPPY BIRTHDAY, LEO, in letters large enough to be read from space. Beside her, Bill held a clipboard upside down. “Why,” Molly whispered, “does your plan say ‘acquire presents’ and then draw a picture of a sandwich?” “It’s a symbol,” Bill said. “The sandwich represents our getaway.” “Our getaway is a sandwich?” “It’s a very fast sandwich.” Molly snatched the clipboard. The party was in full swing: children raced across the lawn, adults guarded the cake, and a mountain of brightly wrapped gifts occupied the porch. She pointed to it. “We go in, blend with the guests, and leave with every present.” “Every one?” Bill asked. “Even the enormous one?” “Especially the enormous one. It may contain a pony.” “Or a smaller, angrier present.” A boy in a paper crown burst through the front door, chased by a woman carrying a tray of cupcakes. Bill ducked so quickly his hat landed in the shrub. Molly plucked it out. “You’re supposed to look inconspicuous.” “I am inconspicuous. The shrub is suspicious.” “You’re wearing a purple velvet coat.” “It’s my stealth coat.” “It has gold buttons.” “Stealth can be glamorous.” They watched the guests gather around the cake. Leo, the birthday boy, stood in the middle of them, grinning as his friends sang. The presents waited near the porch rail, each one decorated with bows, ribbons, and the occasional sticker shaped like a dinosaur. Bill’s expression softened. “That little one’s got a hand-drawn card.” “Don’t get sentimental,” Molly said. “We’re professionals.” “I’m not sentimental. I’m assessing the card’s resale value.” “Cards are worth nothing.” “Not if there’s money inside.” “Bill.” “Fine. No stealing the card.” Molly produced two party hats from her coat pockets. One had a smiling sun; the other said BIRTHDAY BOSS. “We walk in, congratulate the child, and carry the gifts out under the cover of celebration.” “Excellent,” Bill said. “What do we say if anyone asks who we are?” “Cousins.” “Whose cousins?” “Everyone’s. We’re very popular.” They crossed the street with the deliberate cheer of people who had never committed a crime and were hoping nobody asked. At the gate, a little girl handed them each a paper plate. “Are you the magicians?” she asked. Molly glanced at Bill. “We can be.” “Great,” said the girl. “Make my uncle disappear. He keeps eating the frosting.” Inside, the party roared. Bill was immediately recruited to wear a dragon costume, while Molly was given a wand and appointed assistant magician. Their elaborate plan dissolved beneath a shower of confetti. When the children demanded a trick, Molly sighed and pulled a coin from Bill’s ear. It was followed by a button, a cracker, and one small, crumpled note. Bill stared at the note. “That was my getaway money.” Leo laughed so hard he nearly toppled into the cake. Molly looked at the mountain of presents, then at the delighted children. “New plan,” she whispered. “We steal the cake.” Bill eyed the frosting. “Finally. A job with a clear objective.”
created_at
"2026-09-23T08:20:43.162Z"
9/23/2026, 8:20:43 AM
model
"openai/gpt-6-luna-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3428
moderation_latency
(null)
generation_time
13670
tokens_prompt
75
tokens_completion
1258
native_tokens_prompt
66
native_tokens_completion
1221
native_tokens_completion_images
0
native_tokens_reasoning
493
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
0.0006171
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790151643-goJe96PvQgCOwAEdySgx"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790151643-ylje2NaTkyYGsRjHSs1Q"
upstream_id
"resp_0693ad74674e0980016ab38bdb40d487d1a6430ec149ce369e"
provider_responses
0
endpoint_id
"05e94e02-b9c2-4bbb-ba55-4082ee9ad687"
id
"resp_0693ad74674e0980016ab38bdb40d487d1a6430ec149ce369e"
is_byok
false
latency
289
model_permaslug
"openai/gpt-6-luna-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.0006171
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
6.09%
Matches word count
n/a
neededClean
false
words
523
0.11%
Dialogue to Total Word Ratio
Ratio: 38.36%, Deviation: 11.64%
neededClean
false
wordsTotal
524
wordsDialogue
201
3.1024%