NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M36P0552MX1E33K3WDZ5NJKS
Run Details
Model:
GPT-6 Luna
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
12.6s
Cost:
$0.000442
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
5.13%
Dialogue to Total Word Ratio
(details)
2.5642%
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 through the front door,” Molly whispered. Bill stared at her. “That’s your plan?” “It’s a children’s party, Bill. The front door will be open.” “It’ll also be full of children.” “Excellent observation. You’re wasted in crime.” They crouched behind a hedge across from the community hall. Through the windows came the shrieks of a dozen excited children, the thump of party music, and an adult voice attempting to organize a game of musical statues. Bill adjusted his black sweater. “I thought we were breaking in.” “We are. Politely.” “With what disguises?” Molly held up two paper hats. One had a cartoon dinosaur on it. The other said BIRTHDAY VIP in glittery letters. Bill examined his hat. “This is not a disguise. It’s a cry for help.” “Put it on.” “I look like a man who lost a bet.” “You look like a man who’s been invited.” “By whom?” “By the hat.” He put it on. “If anyone asks, I’m the magician.” “You can’t do magic.” “I can make a wallet disappear.” “That’s stealing.” “Exactly. I’m staying in character.” Molly pointed toward the hall. “We enter during the cake.” “Why during the cake?” “Everyone will be watching the birthday child.” “And we’ll be watching the presents?” “We’ll be carrying them.” Bill frowned. “There are children in there, Molly.” “Yes.” “Small children.” “Still yes.” “Some of them may be emotionally attached to those presents.” “They haven’t opened them yet. They don’t know what they’re attached to.” “That is the bleakest thing you’ve ever said.” “You once stole a garden gnome and made it wear your socks.” “It looked cold.” A sudden cheer rose from inside. Molly checked her watch. “Cake time.” “Right,” Bill said, straightening his hat. “Remember, I’m the magician.” “Don’t perform any tricks.” “What if someone asks?” “Say you specialize in disappearing.” They slipped through the open door. A woman holding a tray of cupcakes glanced over. “Hello!” she said. “Are you with the entertainment?” Bill bowed. “I’m the magician.” Molly smiled. “And I’m his assistant.” “Lovely! The children are just sitting down. Would you like some cake?” Bill’s eyes flicked toward a mountain of wrapped gifts beside the coat rack. “I would, but I’m on a strict diet.” The woman laughed. “Then you’re in the wrong room.” Molly nudged him. “We’ll perform after cake.” “Wonderful,” said the woman. “The children love magic.” “Do they love it more than cake?” Bill asked. “No.” “Good. We’ll wait.” They edged toward the presents. A little girl appeared beside them, holding a paper plate. “Are you stealing the presents?” Bill froze. “No.” Molly crouched to her height. “We’re moving them somewhere safe.” “Why?” “Because Bill’s magic is very powerful.” The girl looked at Bill’s hat. “He doesn’t look powerful.” “He’s building suspense,” Molly said. The girl considered this. “Can he make my broccoli disappear?” “Certainly,” Bill said. “Then prove it.” Molly grabbed his sleeve. “We’re not stealing the broccoli.” “I wasn’t going to.” The girl pointed toward the gift pile. “Those are for me.” Bill’s shoulders slumped. “I’m beginning to think we should leave.” “Good,” Molly said. “Let’s go.” “But we haven’t taken anything.” “Exactly. It’s our cleanest job.” As they retreated, the woman handed them two cupcakes. “Thanks for entertaining the children!” Bill accepted his. “We didn’t do anything.” “Best magic trick I’ve seen all day,” she said. Outside, Molly took a bite of her cupcake. Bill looked back at the hall. “We came to steal all the presents and left with frosting.” “Not bad,” Molly said. “Next time, we target the adults’ car keys.” “Are there cupcakes?” “Bill.” “Planning matters.”
created_at
"2026-09-23T08:27:01.163Z"
9/23/2026, 8:27:01 AM
model
"openai/gpt-6-luna-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2884
moderation_latency
(null)
generation_time
12558
tokens_prompt
75
tokens_completion
1117
native_tokens_prompt
66
native_tokens_completion
871
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
0.0004421
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790152021-p6L17tH8twuYiu2nS2MN"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790152021-YNP1gr6uSTmGvWZd07vS"
upstream_id
"resp_00967f542599ed70016ab38d55465c87d187f4a2299ccca4fd"
provider_responses
0
endpoint_id
"05e94e02-b9c2-4bbb-ba55-4082ee9ad687"
id
"resp_00967f542599ed70016ab38d55465c87d187f4a2299ccca4fd"
is_byok
false
latency
1868
model_permaslug
"openai/gpt-6-luna-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.0004421
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
0.00%
Matches word count
n/a
neededClean
false
words
602
5.13%
Dialogue to Total Word Ratio
Ratio: 62.29%, Deviation: 7.71%
neededClean
false
wordsTotal
602
wordsDialogue
375
2.5642%