NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M36NJ4M0B765HS0E5GZ7QZT3
Run Details
Model:
GPT-6 Luna
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
5.1s
Cost:
$0.000167
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
50.28%
Dialogue to Total Word Ratio
(details)
25.1424%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 the party map across the bonnet of their getaway van. A cartoon dinosaur grinned beneath the words HAPPY SIXTH BIRTHDAY, while Bill studied the pencilled route with a thief’s seriousness and a birthday clown’s shoes. “The presents are under the snack table,” Molly whispered. Bill nodded. “And the snacks?” “Collateral.” They had dressed as entertainers: Molly wore a magician’s cape, Bill a papier-mâché moon. Unfortunately, the moon had a face, and it looked exactly like their wanted posters. He turned it around. The plan was simple. Molly would announce a disappearing rabbit. Bill would distract the parents by pretending to be a professional balloon artist. Then they would load the presents into a giant gift bag and stroll out before anyone noticed. “What if a child asks for a balloon?” Molly said. “I’ll make one.” “You can’t make balloons.” “I can make promises.” Inside, the party roared with sugar-fuelled chaos. Molly stepped onto a chair and flourished a wand. Bill squeezed a balloon until it squeaked like a startled mouse. Every child stared. Then the birthday boy pointed at Bill’s moon head. “That’s the man from the picture!” The parents turned. Molly grabbed the gift bag. Bill grabbed the cake. They escaped through the kitchen, pursued by six children and one furious magician’s rabbit. Outside, they discovered the bag contained only wrapping paper. Bill sighed. “At least we got cake.” Molly glanced back at the party. “Next time, we steal the balloons.”
created_at
"2026-09-23T08:19:21.863Z"
9/23/2026, 8:19:21 AM
model
"openai/gpt-6-luna-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1566
moderation_latency
(null)
generation_time
5068
tokens_prompt
75
tokens_completion
408
native_tokens_prompt
66
native_tokens_completion
320
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
0.0001666
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790151561-7gAC2lf9SShzD1qQ2BQX"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790151561-XRJCkai48MlGWt0UqcaL"
upstream_id
"resp_0f5acbfb46da351b016ab38b89f33c87d199502be1a818a4fd"
provider_responses
0
endpoint_id
"05e94e02-b9c2-4bbb-ba55-4082ee9ad687"
id
"resp_0f5acbfb46da351b016ab38b89f33c87d199502be1a818a4fd"
is_byok
false
latency
352
model_permaslug
"openai/gpt-6-luna-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.0001666
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
50.28%
Dialogue to Total Word Ratio
Ratio: 19.11%, Deviation: 9.11%
neededClean
false
wordsTotal
246
wordsDialogue
47
25.1424%