NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M36NJ062EP97RG853363SF7J
Run Details
Model:
GPT-6 Luna (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
24.1s
Cost:
$0.001078
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
99.74%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.8722%
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
Molly unfolded a napkin map of the hall. Bill studied it upside down, wearing a party hat from their car. “Molly, why does your map say ‘cake’ where the exit should be?” “Because the cake is our first obstacle, Bill. It’s guarded by seven-year-olds and one suspicious aunt.” “Then we wait until they sing.” “Excellent. During the song, nobody can hear the presents being politely asked to come with us.” “Presents don’t answer.” “Not with that attitude.” “Your sack says ‘Happy Birthday, Grandma.’” “It’s camouflage.” “For a children’s party?” “Children respect grandmothers.” “Children respect the piñata more.” “Then we’ll disguise ourselves as piñatas.” “Bill, you’re wearing a lampshade.” “It’s a very exclusive piñata.” “What if someone asks why we’re taking every present?” “I’ll say we’re the delivery team.” “Delivery team to where?” “Somewhere with fewer balloons.” “That’s not a destination.” “Neither is this plan, apparently.” “Look, Molly, we could take the gifts, or we could leave them and steal the enormous chocolate cake.” “Bill, stealing cake is still stealing.” “True. But the cake has no name tags.” “Fine. We’ll leave everything, apologize, and ask whether there’s cake for guests, too.” “We should probably go home now.”
created_at
"2026-09-23T08:19:17.321Z"
9/23/2026, 8:19:17 AM
model
"openai/gpt-6-luna-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
10970
moderation_latency
(null)
generation_time
24048
tokens_prompt
75
tokens_completion
629
native_tokens_prompt
66
native_tokens_completion
2143
native_tokens_completion_images
0
native_tokens_reasoning
1845
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
0.0010781
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790151557-MDTXAcZ5JU0KWBdiO0Ca"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790151557-uBEXr0fxiIhxpYABC0Mm"
upstream_id
"resp_0c4b023a22bfed7c016ab38b856e0c87d1969e58ac8e3df04a"
provider_responses
0
endpoint_id
"05e94e02-b9c2-4bbb-ba55-4082ee9ad687"
id
"resp_0c4b023a22bfed7c016ab38b856e0c87d1969e58ac8e3df04a"
is_byok
false
latency
353
model_permaslug
"openai/gpt-6-luna-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.0010781
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
99.74%
Matches word count
n/a
neededClean
false
words
196
100.00%
Dialogue to Total Word Ratio
Ratio: 89.90%, Deviation: 0.10%
neededClean
false
wordsTotal
198
wordsDialogue
178
99.8722%