NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M36NYRSCFJXDY1C65HTDE6Y0
Run Details
Model:
GPT-6 Luna
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
6.3s
Cost:
$0.000168
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
3.62%
Matches word count
(details)
85.85%
Dialogue to Total Word Ratio
(details)
44.7359%
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
Molly spread the map across the laundromat’s folding table. “The party’s in the blue house. Presents are stacked beneath the cake.” Bill studied the map upside down. “And the children?” “Small. Loud. Probably armed with balloons.” “Then we need disguises.” He produced two paper crowns. “Royalty.” “We’re stealing toys, Bill, not annexing the kingdom.” He put on a crown. “You’re right. We’ll pose as entertainers.” Molly eyed his accordion. “You can’t play.” “I can make it look musical.” “That’s worse.” They crept toward the garden gate, where a painted sign announced: WELCOME, PIRATES! Molly tied a black scarf over one eye. Bill wore both crowns. “You look like a pirate who’s lost his ship,” she whispered. “I’m undercover as a birthday king.” Inside, children shrieked around a mountain of wrapped gifts. Bill froze. “Which one holds the expensive stuff?” “The tags say ‘from Grandma.’” He reached for a glittering box. A little girl appeared beside him. “Are you the magician?” Bill glanced at Molly. She sighed and pulled a rabbit from her coat pocket. “Pick a card,” she said. The children surged forward. In the confusion, Bill escaped with a party hat, three cupcakes, and one present labeled TO THE THIEVES. Molly opened it outside. “A book about honesty.” Bill considered this. “We should return it.” “Finally,” said Molly, “a plan with an ending.”
created_at
"2026-09-23T08:26:15.731Z"
9/23/2026, 8:26:15 AM
model
"openai/gpt-6-luna-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2309
moderation_latency
(null)
generation_time
6319
tokens_prompt
75
tokens_completion
394
native_tokens_prompt
66
native_tokens_completion
323
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
0.0001681
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790151975-zAWQxEFrIbzdYY6jNhdC"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790151975-k6vuzmwEwBxfAYlvtZ6O"
upstream_id
"resp_021a6be233218757016ab38d27d3e887d1b67c02498654cc19"
provider_responses
0
endpoint_id
"05e94e02-b9c2-4bbb-ba55-4082ee9ad687"
id
"resp_021a6be233218757016ab38d27d3e887d1b67c02498654cc19"
is_byok
false
latency
930
model_permaslug
"openai/gpt-6-luna-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.0001681
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
3.62%
Matches word count
n/a
neededClean
false
words
224
85.85%
Dialogue to Total Word Ratio
Ratio: 43.75%, Deviation: 6.25%
neededClean
false
wordsTotal
224
wordsDialogue
98
44.7359%