NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M36P510D4QDYJ0F66YK4DNHB
Run Details
Model:
GPT-6 Luna (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
27.0s
Cost:
$0.001114
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
97.63%
Matches word count
(details)
82.39%
Dialogue to Total Word Ratio
(details)
90.0066%
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, the party’s in there, and every present is ours for the taking.” “Bill, you said we were casing a birthday party, not declaring war on wrapping paper.” “What’s the plan?” “We stroll in, blend with the grown-ups, and leave with the gift pile.” “Molly, we’re wearing black turtlenecks.” “Festive black.” “And you’re carrying a sack marked ‘Definitely Not Presents.’” “Also, you brought a crowbar.” “For opening stubborn gift bags.” “Those are paper.” “Molly, we need confidence.” “They suspect exactly two adults at a children’s party.” “Then we act like relatives.” “Whose relatives?” “Yours. You have the face of an uncle.” “I have the face of a wanted poster.” “What if the children ask who we are?” “We say we’re the entertainment.” A shriek of laughter burst from inside. “Was that a child?” “Bill, look through the window. They’ve made a card for the birthday girl.” “‘Thank you for coming, everyone.’” “Someone made us a card?” “No, that’s the invitation.” “I’m keeping it. It’s the only present we’ve earned.” “We haven’t earned anything.” “Then let’s go.” “Empty-handed?” “Bill, we came to steal gifts from children.” “Right. Let’s leave before I start feeling like a villain.” “You already have the turtleneck.” “Then I’ll be a villain with boundaries.”
created_at
"2026-09-23T08:29:40.756Z"
9/23/2026, 8:29:40 AM
model
"openai/gpt-6-luna-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
24998
moderation_latency
(null)
generation_time
26971
tokens_prompt
75
tokens_completion
387
native_tokens_prompt
66
native_tokens_completion
2215
native_tokens_completion_images
0
native_tokens_reasoning
1903
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
0.0011141
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790152180-G37Z5iCKZH2esJx0dOh2"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790152180-hp1UE3w71atRhYeE3E9T"
upstream_id
"resp_088d67fc0c18dd36016ab38df4dd2087d1b4606e2c99f211af"
provider_responses
0
endpoint_id
"05e94e02-b9c2-4bbb-ba55-4082ee9ad687"
id
"resp_088d67fc0c18dd36016ab38df4dd2087d1b4606e2c99f211af"
is_byok
false
latency
3387
model_permaslug
"openai/gpt-6-luna-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.0011141
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
97.63%
Matches word count
n/a
neededClean
false
words
207
82.39%
Dialogue to Total Word Ratio
Ratio: 96.63%, Deviation: 6.63%
neededClean
false
wordsTotal
208
wordsDialogue
201
90.0066%