NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M36NXDJ1P87EXPM4RWYWCFTP
Run Details
Model:
GPT-6 Luna
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
8.1s
Cost:
$0.000185
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
98.03%
Dialogue to Total Word Ratio
(details)
49.0161%
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 floor plan across the hood of their getaway van. “The presents are beside the cake,” she whispered, circling a box with her finger. Bill peered at the map. “That’s the bounce castle.” “It’s a very festive floor plan.” Their target was a children’s party in the community hall, where a towering pile of wrapped gifts stood beneath a banner reading HAPPY BIRTHDAY, NED. Molly had studied the security arrangements: one exhausted magician, three parents with cameras, and a dog dressed as a pirate. They entered disguised as entertainers. Bill wore a rabbit costume; Molly carried a tray of cupcakes. The children greeted them with suspicious excitement, which was not included in the plan. “Are you the real magician?” a small girl asked. “Absolutely,” Molly said. “Watch closely.” She made Bill disappear behind the bounce castle. The children applauded. Bill emerged from the other side, tangled in a net and pursued by the pirate dog. Molly seized the opportunity to slide a gift into her cupcake tray. Then another. Soon the tray resembled a leaning tower of paper and ribbon. Bill limped over. “We should leave.” “After the presents,” she said. A parent approached, smiling. Molly shoved the tray into Bill’s arms and began singing “Happy Birthday.” Everyone joined in, including the dog, who howled magnificently. They escaped through the kitchen, gifts intact, leaving behind a birthday card signed: To Ned, from the magicians. In the van, Bill examined a small parcel. “This one says ‘Best Grandma.’” Molly sighed. Their first job as professional thieves had yielded six sweaters, a puzzle, and one extremely judgmental greeting card.
created_at
"2026-09-23T08:25:31.471Z"
9/23/2026, 8:25:31 AM
model
"openai/gpt-6-luna-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3421
moderation_latency
(null)
generation_time
8108
tokens_prompt
75
tokens_completion
445
native_tokens_prompt
66
native_tokens_completion
357
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
0.0001851
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790151931-Shwq1xim0NwaboV6UVNH"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790151931-vrjAou7XAh4bNXi1mXZG"
upstream_id
"resp_0f637d2f0134c061016ab38cfb96a487d1b56e6ca313bf6117"
provider_responses
0
endpoint_id
"05e94e02-b9c2-4bbb-ba55-4082ee9ad687"
id
"resp_0f637d2f0134c061016ab38cfb96a487d1b56e6ca313bf6117"
is_byok
false
latency
2235
model_permaslug
"openai/gpt-6-luna-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.0001851
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
269
98.03%
Dialogue to Total Word Ratio
Ratio: 13.75%, Deviation: 3.75%
neededClean
false
wordsTotal
269
wordsDialogue
37
49.0161%