NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M36NV1JSBKC3H76F0VV6FJTT
Run Details
Model:
GPT-6 Luna
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
5.9s
Cost:
$0.000179
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
97.69%
Dialogue to Total Word Ratio
(details)
48.8455%
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 unfolded a map across the bonnet of the getaway car. Bill held one corner down with a sausage roll. “The presents are in the living room,” she whispered. “We enter through the garden gate, blend in, and leave with everything.” “Blend in how?” Molly pointed at his suit. “You’re wearing a clown nose.” “It’s a disguise.” “It’s attached to a bicycle horn.” “Authentic clown equipment.” She sighed. Beyond the fence, children shrieked around a bouncy castle. A banner announced: HAPPY BIRTHDAY, TIMMY. Bill adjusted his bow tie, which was shaped like two tiny cupcakes. “We need a diversion,” Molly said. “I can juggle.” “You can drop.” “Then they’ll watch the floor. You take the presents.” Molly studied the map. “The parents will be near the cake. We slip inside during the singing.” “And if they ask who we are?” “We’re the hired entertainment.” Bill brightened. “I’ll do my famous balloon animals.” “Last time, you made a balloon that looked like a frightened eel.” “It was a giraffe.” A door opened. A woman stepped onto the lawn, carrying a tray of juice boxes. Molly ducked behind the car. Bill stood tall and honked his nose. The woman smiled. “You must be the clown!” Bill bowed. “And this is my assistant.” Molly emerged, holding the map upside down. “Wonderful,” said the woman. “The children are waiting.” Molly glanced at Bill. “We’re in.” Bill whispered, “Do clowns get cake?” “Only if they steal it first.”
created_at
"2026-09-23T08:24:13.663Z"
9/23/2026, 8:24:13 AM
model
"openai/gpt-6-luna-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1893
moderation_latency
(null)
generation_time
5925
tokens_prompt
75
tokens_completion
417
native_tokens_prompt
66
native_tokens_completion
344
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
0.0001786
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790151853-nBw5wl4UDIsXNHerEwOI"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790151853-8DKcsHAf2JjBLxEgjW6w"
upstream_id
"resp_073f449666457097016ab38cadc11487d19dcac2b5a0e07730"
provider_responses
0
endpoint_id
"05e94e02-b9c2-4bbb-ba55-4082ee9ad687"
id
"resp_073f449666457097016ab38cadc11487d19dcac2b5a0e07730"
is_byok
false
latency
468
model_permaslug
"openai/gpt-6-luna-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.0001786
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
243
97.69%
Dialogue to Total Word Ratio
Ratio: 53.91%, Deviation: 3.91%
neededClean
false
wordsTotal
243
wordsDialogue
131
48.8455%