NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-09-01KX4181N9KPMQDTJ2VV7127AK
Run Details
Model:
GPT-5.6 Luna (Reasoning)
Test:
Dialogue tags
Scenario:
Write 500 words with 30% dialogue
Duration:
6.0s
Cost:
$0.005772
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
1.18%
Dialogue to Total Word Ratio
(details)
0.5903%
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 crouched behind the hedge, studying the birthday house through binoculars that had been designed for bird-watching and were therefore painted with tiny blue tits. Across the lawn, paper lanterns bobbed in the evening breeze, a clown-shaped piñata hung from an apple tree, and a handwritten sign announced: WELCOME, JEREMY! NO ADULTS IN THE PRESENT ROOM. Bill adjusted his black turtleneck, which was too warm for July and covered in cat hair. “The sign says no adults, Molly. We’re not adults. We’re professionals.” “We’re thirty-eight and you still owe me money from the museum job.” “That was an investment.” “You invested my money in a vending machine.” “It was a promising vending machine.” Behind them, their getaway vehicle—a battered ice-cream van borrowed from Bill’s cousin—gave a mournful chime. Molly flinched. The van had been silent all afternoon, but apparently it objected to crime after sunset. The plan was simple. They would enter through the back door during the magician’s performance, cross the kitchen, and remove every present from the dining room. Bill had constructed two enormous sacks from old theater curtains. Molly had brought disguises: one pirate hat, two rubber noses, and a plastic wand that squeaked whenever waved. The back door stood open. A trail of floury footprints led inside, suggesting either a careless cook or a remarkably clumsy ghost. Molly slipped across the grass. Bill followed, carrying the sacks and trying not to trip over the piñata’s dangling rope. “Remember,” Molly whispered, “we take the presents and leave. No cake, no balloons, no interacting with children.” “What if they ask us to dance?” “Especially then.” They reached the kitchen just as a burst of applause thundered from the sitting room. The magician shouted something about escaping from a locked box. Bill peered around the doorframe and saw a dozen children staring at a bearded man in sequins. On the table beside him sat a chocolate cake shaped like a rocket. “Molly,” Bill murmured, “the cake has a launch countdown.” “Focus.” They crept into the dining room. Gifts were stacked beneath a banner, wrapped in bright paper and decorated with bows. Bill opened his first sack. Molly began loading presents with the grim efficiency of a librarian reshelving books. A small cardboard box rattled. Bill froze. “That one’s alive.” “It’s probably a toy.” “It growled.” Molly snatched it from him and read the label. “To Jeremy, from Aunt Paula. Hamster.” “Do we steal the hamster?” “We steal everything.” The box rattled again, more indignantly. From the sitting room came a child’s voice. “Where’s Pickles?” Molly and Bill stared at each other. Somewhere beneath the table, the family dog began barking. Bill shoved the hamster into his coat, where it immediately started chewing his shirt. “New plan,” Molly said. “We leave the presents.” “And the hamster?” “We return the hamster.” They sprinted through the kitchen, pursued by the dog, three children, and the magician, who had escaped his box but not his handcuffs. Bill leapt into the ice-cream van. Molly slammed the door behind him. The engine coughed, the chime rang, and the van rolled directly into the hedge. From inside Bill’s coat, Pickles squeaked. “Successful?” he asked. Molly looked at the untouched presents, the collapsing hedge, and the hamster chewing through Bill’s collar. “Spectacularly,” she said.
created_at
"2026-07-09T18:11:39.827Z"
7/9/2026, 6:11:39 PM
model
"openai/gpt-5.6-luna-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1837
moderation_latency
(null)
generation_time
5560
tokens_prompt
77
tokens_completion
956
native_tokens_prompt
66
native_tokens_completion
951
native_tokens_completion_images
0
native_tokens_reasoning
201
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
0.005772
router
(null)
provider_responses
0
endpoint_id
"eebea444-34a5-4642-a766-cb319471d33a"
id
"resp_0532ce6d72f3da97016a4fe45be41481969b96a77d0299471c"
is_byok
false
latency
309
model_permaslug
"openai/gpt-5.6-luna-20260709"
provider_name
"OpenAI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer
(null)
request_id
"req-1783620699-v4Ry6Tb190xJvgLlXJYo"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1783620699-GUb3qFhb6BafWQwawJnS"
upstream_id
"resp_0532ce6d72f3da97016a4fe45be41481969b96a77d0299471c"
total_cost
0.005772
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
549
1.18%
Dialogue to Total Word Ratio
Ratio: 20.58%, Deviation: 9.42%
neededClean
false
wordsTotal
554
wordsDialogue
114
0.5903%