NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M36P0VJD5959Y7SSEM281NJK
Run Details
Model:
GPT-6 Luna (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
30.2s
Cost:
$0.001470
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
92.82%
Dialogue to Total Word Ratio
(details)
96.4118%
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 a crumpled floor plan across the laundromat table, pinning its corners with a sock, a spoon, and Bill’s emergency biscuit. Outside, rain tapped the windows like impatient accomplices. The map showed a birthday party, twelve children, one exhausted clown, and a mountain of brightly wrapped presents awaiting rescue. “Entry is simple,” Molly said. “We arrive disguised as entertainers, distract the adults, and leave with every present.” Bill squinted. “What entertainment?” “Balloon animals.” “I can make a balloon look like a sausage.” “Perfect. Children love sausages.” “Do they?” “At least, they’ll remember us,” Molly promised. “That’s reassuring, probably, maybe.” Bill practiced a bow, knocking over the biscuit. Molly retrieved it and inspected the wrapper for crumbs, fingerprints, or clues connecting them to previous snack-related crimes. Their plan required precision, quiet shoes, and a getaway vehicle small enough to park beside the inflatable castle without attracting parental suspicion or whistles. “Use the clown’s van,” Bill proposed. “It has painted stars.” “Those are dents,” Molly said. “Stars are dents with ambition.” “Fine. You drive. I’ll collect gifts.” “What if a child catches us?” “Then we’re the surprise party.” “That makes no sense.” “Neither does a clown at breakfast wearing tap shoes.”
created_at
"2026-09-23T08:27:24.116Z"
9/23/2026, 8:27:24 AM
model
"openai/gpt-6-luna-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4463
moderation_latency
(null)
generation_time
30208
tokens_prompt
75
tokens_completion
729
native_tokens_prompt
66
native_tokens_completion
2926
native_tokens_completion_images
0
native_tokens_reasoning
2641
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
0.0014696
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790152044-u5hVMkJWw6F1G4xYejvw"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790152044-4s72a7DwVh1Ca0xRzwCw"
upstream_id
"resp_0260c06426edf5f1016ab38d6c33b487d1aad6e04266340d77"
provider_responses
0
endpoint_id
"05e94e02-b9c2-4bbb-ba55-4082ee9ad687"
id
"resp_0260c06426edf5f1016ab38d6c33b487d1aad6e04266340d77"
is_byok
false
latency
1106
model_permaslug
"openai/gpt-6-luna-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.0014696
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
100.00%
Matches word count
n/a
neededClean
false
words
200
92.82%
Dialogue to Total Word Ratio
Ratio: 44.78%, Deviation: 5.22%
neededClean
false
wordsTotal
201
wordsDialogue
90
96.4118%