NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M36NJDRY2DAG8AXF7C3JDXGR
Run Details
Model:
GPT-6 Luna
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
5.7s
Cost:
$0.000188
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
0.03%
Matches word count
(details)
99.58%
Dialogue to Total Word Ratio
(details)
49.8034%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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
“We enter through the cake.” “The cake, Molly?” “It’s a very large cake, Bill. I checked.” “You checked the cake?” “I checked the bakery. The cake is being delivered at three. We’re being delivered at three-oh-five.” “Disguised as cake?” “Disguised as clowns. The cake is our cover.” “I don’t like clowns.” “Neither do children. They’ll flee, leaving the presents unattended.” “Or they’ll ask us to make balloon animals.” “Then make a balloon animal.” “I only know how to make a balloon sword.” “Perfect. It’ll establish authority.” “Over six-year-olds?” “Especially six-year-olds. Now, the gifts are stacked beside the piñata. We grab them, load the wagon, and escape through the garden gate.” “What if someone asks why the clowns are stealing presents?” “We say it’s a surprise.” “For whom?” “For us.” Bill studied the party invitation. “It says ‘No clowns.’” “Then we’ll be the first clowns they’ve ever invited.” “That’s not what it means.” “Bill, confidence is everything. Also, I brought disguises.” She unfolded two enormous flower-patterned jackets. “Those are curtains.” “Exactly. Children love magic.” “Where’s the wagon?” “Outside.” “Where?” “Under the banner that says ‘Happy Birthday.’” “That seems conspicuous.” “It’s festive.” At three-oh-five, they crept toward the gate. A little girl spotted them. “Are you the clowns?” Molly smiled. “We’re the present inspectors.” “Great! Can you inspect my pony?” Bill whispered, “You brought a pony?” “I thought you checked the cake.”
created_at
"2026-09-23T08:19:31.235Z"
9/23/2026, 8:19:31 AM
model
"openai/gpt-6-luna-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1465
moderation_latency
(null)
generation_time
5626
tokens_prompt
75
tokens_completion
468
native_tokens_prompt
66
native_tokens_completion
362
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
0.0001876
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790151571-mi2KoSx048oubVDfYC83"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790151571-bhgHQsHZcGNqv5xzFz3q"
upstream_id
"resp_01680abff6b35a5b016ab38b9358e887d18f73bf4f3955d19d"
provider_responses
0
endpoint_id
"05e94e02-b9c2-4bbb-ba55-4082ee9ad687"
id
"resp_01680abff6b35a5b016ab38b9358e887d18f73bf4f3955d19d"
is_byok
false
latency
384
model_permaslug
"openai/gpt-6-luna-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.0001876
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
0.03%
Matches word count
n/a
neededClean
false
words
230
99.58%
Dialogue to Total Word Ratio
Ratio: 87.45%, Deviation: 2.55%
neededClean
false
wordsTotal
239
wordsDialogue
209
49.8034%