NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M36NH1E3JNDRQ9JM9V8QT77T
Run Details
Model:
GPT-6 Luna
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
5.9s
Cost:
$0.000188
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0025%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 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
“We enter through the bouncy castle,” Molly whispered, studying the party invitation as if it were a bank blueprint. Bill frowned. “That’s not an entrance. That’s a trampoline with delusions.” “Exactly. Nobody suspects a person emerging from a dinosaur’s mouth.” “Children will suspect. Children suspect everything. Last week one accused me of being a magician because I had a deck of cards.” “You were wearing a cape.” “It was raining.” Molly tapped the map. “The presents are stacked beside the cake. We grab the pile, glide out, and vanish.” “Glide how?” “I’ve brought roller skates.” “To a children’s party?” “Disguise.” Bill considered this. “I’m not skating past six-year-olds. They’ll challenge me to races. I’m vulnerable to competition.” “You’re vulnerable to cupcakes, too. Focus.” The bouncy castle shuddered. A small voice called, “Is there a grown-up in there?” Bill froze. “I think the dinosaur has a witness.” “Act natural.” “I’m dressed as a pirate.” “Then act pirate-natural.” Bill poked his head through the rubber jaws. “Arrr, I’m here to inspect the treasure!” A child pointed at him. “That’s my uncle.” Molly lowered the present sack. “Your uncle?” “Usually he wears the cape.” Bill sighed. “I knew the rain would ruin everything.” Molly handed the sack to the child. “Fine. We’ll steal the cake instead.” The child grinned. “You’ll need roller skates for that.” “Not again,” Bill groaned. “Race you!” the child shouted. Bill fled on skates, pursued by children, balloons, and one deeply offended dinosaur.
created_at
"2026-09-23T08:18:45.988Z"
9/23/2026, 8:18:45 AM
model
"openai/gpt-6-luna-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1689
moderation_latency
(null)
generation_time
5648
tokens_prompt
75
tokens_completion
453
native_tokens_prompt
66
native_tokens_completion
363
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
0.0001881
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790151526-noMDj2Og0PopfxiRi54Q"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790151526-FSfhvpj6mrvQoNiwt4Ac"
upstream_id
"resp_0064259b83b9194c016ab38b662df087d1ae323713acdbd797"
provider_responses
0
endpoint_id
"05e94e02-b9c2-4bbb-ba55-4082ee9ad687"
id
"resp_0064259b83b9194c016ab38b662df087d1ae323713acdbd797"
is_byok
false
latency
400
model_permaslug
"openai/gpt-6-luna-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.0001881
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
0.00%
Matches word count
n/a
neededClean
false
words
244
0.00%
Dialogue to Total Word Ratio
Ratio: 67.74%, Deviation: 17.74%
neededClean
false
wordsTotal
248
wordsDialogue
168
0.0025%