NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M36P13E976FD9MZX09EY24BC
Run Details
Model:
GPT-6 Luna
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
5.2s
Cost:
$0.000166
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
86.38%
Matches word count
(details)
26.24%
Dialogue to Total Word Ratio
(details)
56.3111%
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
“Right,” Molly whispered, studying the birthday-party invitation through binoculars. “We enter at seven, locate the presents, and leave before anyone notices.” “Why are you whispering?” Bill asked. “Because we’re thieves.” “We’re outside a bouncy castle.” “Exactly. The children are unpredictable.” Bill peered over the garden fence. “I count twelve children, three adults, and one terrifying clown.” “That’s the birthday boy’s uncle.” “How can you tell?” “He’s holding a tiny dog and crying.” “Fine. What’s the plan?” “We pose as magicians.” “I can’t do magic.” “You once made a whole tray of cupcakes disappear.” “I ate them.” “Same principle. Now, when I distract everyone, you take the presents.” “What if they’re heavy?” “They’re wrapped in cheerful paper, Bill, not cast iron.” “What if a child catches us?” “Tell them we’re the surprise.” “I hate being the surprise.” “You hate being caught more.” Bill glanced at the enormous pile of gifts. “There’s a bicycle in there.” “Excellent. We can ride it out.” “It’s a child’s bicycle.” “Then pedal quickly.” A party horn blared. Bill flinched and dropped the invitation. Molly snatched it up. “That’s our cue.” “For what?” “To go home.” “Finally, a plan I understand.” They crept away. “Wait,” said Bill. “You’re leaving the binoculars.” “Let them keep them. It’s a birthday.”
created_at
"2026-09-23T08:27:32.175Z"
9/23/2026, 8:27:32 AM
model
"openai/gpt-6-luna-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2422
moderation_latency
(null)
generation_time
5206
tokens_prompt
75
tokens_completion
418
native_tokens_prompt
66
native_tokens_completion
318
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
0.0001656
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790152052-a5iZl0RAEL3VWjL233nY"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790152052-ZaZxI2KeqALi2VcCUAsx"
upstream_id
"resp_0d223be5d56917f1016ab38d747be487d1bd0c4cc2ff25fd55"
provider_responses
0
endpoint_id
"05e94e02-b9c2-4bbb-ba55-4082ee9ad687"
id
"resp_0d223be5d56917f1016ab38d747be487d1bd0c4cc2ff25fd55"
is_byok
false
latency
995
model_permaslug
"openai/gpt-6-luna-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.0001656
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
86.38%
Matches word count
n/a
neededClean
false
words
211
26.24%
Dialogue to Total Word Ratio
Ratio: 79.25%, Deviation: 10.75%
neededClean
false
wordsTotal
212
wordsDialogue
168
56.3111%