NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M36NVM45QDP78DSFCN9D7TGJ
Run Details
Model:
GPT-6 Luna
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
9.3s
Cost:
$0.000371
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.3564%
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
“We go in at seven,” Molly whispered, crouched behind the hedge. Bill checked his watch. “The invitation says the party starts at two.” “Exactly. By seven, the children will be tired, the cake will be gone, and the presents will be unguarded.” “What about the parents?” “They’ll be distracted.” “By what?” Molly pointed through the hedge. A paper banner sagged over the garden gate: HAPPY BIRTHDAY, OLIVER! Beneath it, a dozen adults were watching a magician produce scarves from a rabbit’s hat. “Magic,” she said. Bill frowned. “That’s a man pulling scarves from a rabbit.” “Magic is whatever keeps people from noticing us.” “And the children?” “Also distracted. Children are easily distracted.” A small boy ran past them wearing a cardboard crown and carrying a wooden sword. Bill ducked. “That one looked alert.” “He’s dressed as a knight. He probably can’t count past ten.” “He can count to eleven,” said a voice behind them. Molly and Bill turned. A girl in a pink party dress stood beside the hedge, holding a cupcake. “Are you stealing the presents?” she asked. “Of course not,” Molly said. “Then why are you hiding in the bushes?” “We’re gardeners,” said Bill. The girl looked at the hedge. “You’re sitting on the flowers.” “We’re very thorough gardeners,” Molly said. The girl took a bite of cupcake. “The presents are in the living room. Mum put them there because Uncle Pete ate one last year.” Bill blinked. “Ate a present?” “He thought it was a chocolate box.” “Was it?” “No. It was a sock.” Bill glanced at Molly. “We’re not stealing socks.” “Not unless they’re valuable,” Molly murmured. The girl pointed toward the house. “The back door’s open. But you’ll have to get past the dog.” “What sort of dog?” Molly asked. “A very small one.” Molly relaxed. “Excellent.” “It bites ankles.” Molly relaxed less. Bill straightened his tie. “We’re leaving.” “Good,” said the girl. “Because I told Mum there were thieves in the hedge.” From the garden came a whistle. The magician’s rabbit shot past them, dragging a string of scarves. The adults cheered. The children shrieked. The tiny dog barked like a broken alarm clock. Molly stood. “We could still go in.” Bill stared at her. “The girl has reported us, the rabbit is loose, and the dog is armed.” “With teeth.” “Ankle teeth.” Molly considered the house, then the girl’s cupcake. “What presents did Oliver get?” “Mostly books,” the girl said. “Books?” Bill turned away. “I’m not risking prison for books.” Molly sighed. “Fine. We’ll leave.” The girl held out the cupcake. “You can have this.” Bill eyed it suspiciously. “Any socks inside?” “No. But there’s a raisin.” He took it. “We’ll split it.” “Get your own,” Molly said. As they crept away, the girl called after them, “Happy birthday, Oliver!” “Happy birthday, Oliver!” Molly called back. Bill swallowed the cupcake in one bite. “You know, this was a terrible heist.” “Terrible,” Molly agreed. “But at least we didn’t steal a sock.” Behind them, the dog barked. Bill hurried. “Yet.”
created_at
"2026-09-23T08:24:32.655Z"
9/23/2026, 8:24:32 AM
model
"openai/gpt-6-luna-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1448
moderation_latency
(null)
generation_time
9191
tokens_prompt
75
tokens_completion
890
native_tokens_prompt
66
native_tokens_completion
729
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
0.0003711
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790151872-X2YTgSmcGBloF0f2rMu5"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790151872-eZ5YOQJberQYOd77oCaz"
upstream_id
"resp_07c860090de6b3a6016ab38cc0dd6887d18640fc46f107b906"
provider_responses
0
endpoint_id
"05e94e02-b9c2-4bbb-ba55-4082ee9ad687"
id
"resp_07c860090de6b3a6016ab38cc0dd6887d18640fc46f107b906"
is_byok
false
latency
461
model_permaslug
"openai/gpt-6-luna-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.0003711
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
0.00%
Dialogue to Total Word Ratio
Ratio: 54.35%, Deviation: 15.65%
neededClean
false
wordsTotal
506
wordsDialogue
275
49.3564%