NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M36NPBCN5N61WMVET6PW1MQQ
Run Details
Model:
GPT-6 Luna (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 500 words with 30% dialogue
Duration:
18.1s
Cost:
$0.000553
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
1.20%
Dialogue to Total Word Ratio
(details)
0.6000%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 30% 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 spread the map across the bonnet of Bill’s car. It was actually a napkin from a diner, and the map was mostly gravy, but the red circle around the community hall looked authoritative. “The presents are under the enormous balloon arch,” she whispered. “We go in, take everything, and leave before anyone notices.” Bill adjusted his bow tie. “What if someone notices?” “Then you’re the magician.” “I’m not a magician.” “You own a cape.” “It’s a bathrobe.” “Exactly. Mysterious.” Across the street, the hall’s windows glowed with party lights. Children darted past them in paper crowns, trailing streamers and shrieks. A banner over the door read HAPPY BIRTHDAY, SAM! in letters that had been individually taped on by a child with strong feelings about spacing. Bill peered at the hall. “You said this would be a quiet job.” “It will be. We’ll simply remove the presents.” “From a children’s party.” “Yes.” “While children are inside.” “That’s why we’ll be dressed as entertainers.” Molly gestured to their costumes: her sequined jacket and Bill’s bathrobe, now decorated with a hand-painted rabbit. The rabbit had one eye and appeared to be asking for help. A small boy pushed open the hall door and stared at them. “Are you the birthday magicians?” Molly smiled. Bill made the rabbit wave. “We are,” Molly said. “Prepare to be amazed.” The boy shouted, “MUM! THE MAGICIANS ARE HERE!” and vanished into the hall. Bill looked at Molly. “We have been hired without consent.” “Excellent. We’re already inside.” They entered to applause. Molly bowed. Bill bowed too, though his bathrobe belt came loose and slid onto the floor. The children laughed so hard that one fell gently into a pile of cushions. Molly seized the moment. “For our first trick, we shall make all the presents disappear!” “Is that wise?” Bill murmured. “Can you think of a better trick?” “I could make your plan disappear.” She whispered, “Focus.” They approached the gift table. Molly picked up a glittering box. A girl with a plastic crown stepped in front of her. “That one’s for Sam,” the girl said. “Of course,” Molly replied. “We’re just checking it for… magical energy.” The girl narrowed her eyes. “You’re bad magicians.” “Harsh,” Bill said. “But not inaccurate.” Sam, the birthday boy, appeared beside them. “Are you going to steal my presents?” Molly froze. Bill’s rabbit drooped against his chest. “We were,” Molly admitted. “But then we met the security team.” The children surrounded them, solemn as tiny detectives. One held a cupcake like evidence. Another had a kazoo. Bill cleared his throat. “We’ve decided to perform a different trick. We’ll make these presents stay exactly where they are.” “And,” Molly added, “we’ll make two suspicious adults disappear.” The children cheered as Molly and Bill backed toward the door. Outside, Bill retrieved his belt from the floor of the hall. “So,” he said, “no presents?” “Not a one.” “Can we at least keep the cape?” “It’s your bathrobe.” “Then I’m keeping it.” From inside came a delighted roar. Molly glanced back through the window. Sam was opening a gift shaped like a lumpy, badly wrapped box. “Look,” Bill said. “A successful heist.” Molly raised an eyebrow. “We stole the show.”
created_at
"2026-09-23T08:21:39.867Z"
9/23/2026, 8:21:39 AM
model
"openai/gpt-6-luna-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
6438
moderation_latency
(null)
generation_time
18038
tokens_prompt
75
tokens_completion
1065
native_tokens_prompt
66
native_tokens_completion
1093
native_tokens_completion_images
0
native_tokens_reasoning
346
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
0.0005531
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790151699-XY2mAuE40b1hgHytQ8ha"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790151699-zWLs3nm5LT5KrQBD8ZW4"
upstream_id
"resp_061f85112825913b016ab38c14061c87d1b27e7681fb0009ee"
provider_responses
0
endpoint_id
"05e94e02-b9c2-4bbb-ba55-4082ee9ad687"
id
"resp_061f85112825913b016ab38c14061c87d1b27e7681fb0009ee"
is_byok
false
latency
395
model_permaslug
"openai/gpt-6-luna-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.0005531
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
537
1.20%
Dialogue to Total Word Ratio
Ratio: 39.41%, Deviation: 9.41%
neededClean
false
wordsTotal
538
wordsDialogue
212
0.6000%