NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M36NH1E8004RCKXNNP2BWM94
Run Details
Model:
GPT-6 Luna
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
5.1s
Cost:
$0.000164
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
99.89%
Dialogue to Total Word Ratio
(details)
49.9431%
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 plan across the hood of the getaway car: a crayon drawing of a birthday cake, three balloons, and a door labeled BACK. “We enter through the kitchen,” she whispered. Bill studied the map. “That’s a window.” “Then we enter through the window.” He nodded gravely, as if this were the sort of strategic flexibility taught at a very expensive criminal academy. Across the street, the children’s party pulsed with music and the shrieks of people who had not yet learned to fear clowns. Their target was a mountain of wrapped presents beside the cake. Molly had brought a sack. Bill had brought a fake mustache, which he insisted made him look like a harmless uncle. They crept around the house and found the kitchen window open. Molly climbed in first, landing among bowls of potato salad. Bill followed, got one leg stuck, and emerged wearing a serving tray like a knight’s shield. A small boy stared at them. “Are you the magicians?” “Absolutely,” Molly said. Bill produced a rabbit from the sack. It was, in fact, a very confused sock puppet. The children applauded. Molly improvised a disappearing act, vanishing the presents into the sack while Bill distracted everyone with a dance that suggested his knees had separate legal counsel. They escaped with the gifts, the cake, and three party hats. In the car, Molly checked the haul. “Mostly toys,” she said. Bill sighed. “We’ll need a bigger getaway car next time.”
created_at
"2026-09-23T08:18:46.047Z"
9/23/2026, 8:18:46 AM
model
"openai/gpt-6-luna-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1420
moderation_latency
(null)
generation_time
4848
tokens_prompt
75
tokens_completion
382
native_tokens_prompt
66
native_tokens_completion
314
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
0.0001636
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790151526-6FDKC8GoYYq8ndMEK9Ev"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790151526-JJ9w4xCJUnscQva10SGx"
upstream_id
"resp_01b88b95a729d3db016ab38b66326c87d1af7c0be1233d70f9"
provider_responses
0
endpoint_id
"05e94e02-b9c2-4bbb-ba55-4082ee9ad687"
id
"resp_01b88b95a729d3db016ab38b66326c87d1af7c0be1233d70f9"
is_byok
false
latency
578
model_permaslug
"openai/gpt-6-luna-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.0001636
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
245
99.89%
Dialogue to Total Word Ratio
Ratio: 11.84%, Deviation: 1.84%
neededClean
false
wordsTotal
245
wordsDialogue
29
49.9431%