NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M36NNQZXNYNG8NN7R9MYXE20
Run Details
Model:
GPT-6 Luna
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
4.6s
Cost:
$0.000172
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
51.93%
Matches word count
(details)
82.81%
Dialogue to Total Word Ratio
(details)
67.3693%
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
“You’re sure this is the children’s party?” Molly whispered. Bill peered through the hedge. “There’s a banner that says HAPPY BIRTHDAY, TIMMY.” “That could be a very enthusiastic accountant.” “And there are thirty-seven balloons.” “Accountants celebrate.” “Look, Molly, the presents are stacked beside the cake. We go in, lift the pile, and leave.” “With thirty children watching?” “They’ll be distracted.” “By what?” Bill produced a kazoo. “The national anthem.” “You can’t play the national anthem on a kazoo.” “I can play something that makes people look around.” Molly adjusted her black mask. “We’re stealing from children.” “We’re borrowing from children. Permanently.” “That’s worse.” “Then we’ll leave them a note.” “What does it say?” “Dear children, your gifts have been seized by the Department of Birthday Redistribution.” “They’ll ask their parents what that means.” “Exactly. Confusion buys us time.” A shriek erupted inside. “Is Timmy crying?” Molly asked. “No. That’s the clown.” “Why is the clown screaming?” “He saw us.” Bill ducked. Molly sighed. “You said this was a quiet job.” “I said we’d be quiet.” “You’re holding a kazoo.” “It’s for emergencies.” “And what’s the emergency?” “The clown’s gaining.” Molly grabbed Bill’s sleeve. “Run.” “Without the presents?” “Bill, we’re thieves, not monsters.” “So we’re stealing the cake?” “No!” “Worth asking,” Bill said, as they sprinted away.
created_at
"2026-09-23T08:21:20.003Z"
9/23/2026, 8:21:20 AM
model
"openai/gpt-6-luna-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1518
moderation_latency
(null)
generation_time
4599
tokens_prompt
75
tokens_completion
447
native_tokens_prompt
66
native_tokens_completion
331
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
0.0001721
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790151680-nNB1z5MgcH8yOd7gGAwb"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790151680-RC5lEvbjJtqkRbXVrUBF"
upstream_id
"resp_04e9f822c86cb6fa016ab38c00174487d1b5eecc2fc245b9ed"
provider_responses
0
endpoint_id
"05e94e02-b9c2-4bbb-ba55-4082ee9ad687"
id
"resp_04e9f822c86cb6fa016ab38c00174487d1b5eecc2fc245b9ed"
is_byok
false
latency
314
model_permaslug
"openai/gpt-6-luna-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.0001721
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
51.93%
Matches word count
n/a
neededClean
false
words
216
82.81%
Dialogue to Total Word Ratio
Ratio: 83.41%, Deviation: 6.59%
neededClean
false
wordsTotal
217
wordsDialogue
181
67.3693%