NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M36NKXHSNSZXCD9EDFC5Z90F
Run Details
Model:
GPT-6 Luna
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
8.5s
Cost:
$0.000378
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
93.65%
Matches word count
(details)
65.16%
Dialogue to Total Word Ratio
(details)
79.4051%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 70% 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
“We go in at three,” Molly whispered, studying the birthday party through binoculars. “That’s when the children are distracted by the magician.” “Or terrified by the magician,” Bill said. “He’s got a rabbit.” “Rabbits are harmless.” “This one’s wearing a tiny top hat. That’s how they start.” Molly lowered the binoculars. “Our objective is the presents. All of them. We enter, gather, exit. No complications.” “Have you ever met a child?” “I’ve met several.” “Briefly. From behind a hedge.” “Children are just small adults with louder shoes.” A shriek came from the garden. Bill flinched. “That one sounded like a kettle being murdered.” “Focus. The gifts are stacked by the patio doors. We use the laundry basket.” “The laundry basket says ‘HAPPY BIRTHDAY, ELLA’ in glitter.” “Then nobody will suspect it.” “They’ll suspect it’s a laundry basket.” “Bill, I’ve planned every detail. You’ll distract the adults.” “How?” “Tell them you’re a magician.” “I’m not a magician.” “Neither is the man with the rabbit, apparently. I saw him pull a sausage from a child’s ear.” “That’s not magic. That’s a health-code violation.” Molly pointed toward the house. “There. The parents are serving cake. We move now.” “Wait. What’s the signal?” “I’ll say, ‘The frosting is compromised.’” “What does that mean?” “It means go.” “Why not say ‘go’?” “Too obvious.” “Who are we hiding from?” “Everyone.” Bill swallowed. “Right. I’ll distract them with a trick.” He stepped onto the lawn and clapped his hands. “Ladies and gentlemen! Observe: the mysterious disappearance of—” A dozen children turned toward him. “—my confidence,” he finished. Molly hurried to the present pile. “Bill, distract them!” “I am! They’re watching.” “They’re watching me.” “Then I’ll distract you.” “Just do something!” Bill pulled a coin from behind a child’s ear. The child stared at him. “That’s my tooth.” Bill examined the coin. “Then I’ve made a terrible mistake.” Molly lifted the laundry basket. “The frosting is compromised!” A parent glanced over. “What?” “Nothing!” Molly said. “We’re with the magician.” “There’s no magician,” the parent said. Bill pointed at the rabbit, which had escaped its tiny top hat and was sprinting beneath the picnic table. “Then who’s that?” The children cheered and gave chase. In the commotion, Molly and Bill filled the basket with presents. “Got them,” Molly whispered. “Now walk naturally.” Bill put the basket on his head. “That’s not natural.” “I’m hiding the presents.” “You’re wearing them.” A small girl appeared beside them. “Those are for my birthday.” Molly froze. “We know.” “Are you taking them?” “We’re transporting them,” Bill said. “For security.” “Why?” He looked at Molly. “Because,” she said, “your parents asked us to.” The girl narrowed her eyes. “They didn’t.” “No,” Molly admitted. “They didn’t.” The girl considered this. “You can have a cupcake if you put them back.” Bill lowered the basket. “Deal.” “Excellent,” Molly said. “The heist is over.” “What about the cupcake?” “Bill, don’t push your luck.” “I wasn’t. I was negotiating.”
created_at
"2026-09-23T08:20:20.16Z"
9/23/2026, 8:20:20 AM
model
"openai/gpt-6-luna-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1286
moderation_latency
(null)
generation_time
8457
tokens_prompt
75
tokens_completion
953
native_tokens_prompt
66
native_tokens_completion
742
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
0.0003776
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790151620-D05W2Bk3DHu3stWqifSD"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790151620-bkgbKpEjh5fuoNyEXJPx"
upstream_id
"resp_074a1c5b0b9a9564016ab38bc442e887d18e420a05bad9c0ef"
provider_responses
0
endpoint_id
"05e94e02-b9c2-4bbb-ba55-4082ee9ad687"
id
"resp_074a1c5b0b9a9564016ab38bc442e887d18e420a05bad9c0ef"
is_byok
false
latency
292
model_permaslug
"openai/gpt-6-luna-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.0003776
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
93.65%
Matches word count
n/a
neededClean
false
words
491
65.16%
Dialogue to Total Word Ratio
Ratio: 67.07%, Deviation: 2.93%
neededClean
false
wordsTotal
492
wordsDialogue
330
79.4051%