NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-09-01KX41BBSCHENB6RBV81XFPED3
Run Details
Model:
GPT-5.6 Luna
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
4.9s
Cost:
$0.004824
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.12%
Dialogue to Total Word Ratio
(details)
0.0594%
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
“Tell me again why we’re robbing a children’s party,” Molly whispered from behind the hedge. “Because children’s parties have presents,” Bill whispered back. “So do weddings.” “Weddings have security, angry relatives, and shrimp with opinions. Children’s parties have balloons.” A yellow balloon bobbed above the garden fence. Beyond it, a banner read HAPPY BIRTHDAY, MILO! A dozen children shrieked around a magician, while a table sagged beneath brightly wrapped gifts. Molly adjusted her black cap. “Our client specifically said all the presents.” “Our client is a six-year-old?” “Our client is a toy manufacturer with a very strange procurement strategy.” Bill peered through binoculars. “I see the target. Red box, blue ribbon. Probably a robot.” “Probably a trap. Children know everything.” “They don’t know fractions.” “They know when someone is touching their cake.” A boy sprinted past the hedge, clutching a plastic sword. “Ninja!” Bill ducked. “We’ve been spotted.” “He was shouting at a butterfly.” “Professional reconnaissance.” Molly unfolded a crumpled map. “We enter through the side gate, cross the lawn, distract the adults, and load the presents into the getaway vehicle.” “You mean the wagon?” “It has wheels.” “It has a missing wheel.” “Three wheels are sufficient for crime.” Bill pointed toward the party. “What’s the adult distraction?” Molly smiled. “You.” “Why me?” “You have the face of a man who has made a terrible decision.” “That’s my natural charm.” “You’ll join the magician’s show.” “I don’t know magic.” “Neither does the magician. He just pulled a sausage out of his sleeve.” “Was it attached to anything?” “Not visibly.” Bill swallowed. “Fine. What do you do?” “I’ll be the party clown.” “You hate clowns.” “I hate their work ethic. I can improve the brand.” They slipped through the gate. Bill marched toward the magician, who was attempting to make a rubber chicken vanish. “Ladies and gentlemen,” Bill announced, “behold! A surprise guest!” The children turned. “Are you a pirate?” a girl asked. “No.” “Are you a burglar?” Bill glanced at Molly, who was already lifting the red box. “Also no.” “Then why are you dressed like one?” “Fashion.” Molly crouched behind the gift table, stacking packages into a canvas sack. “Bill, distract harder.” “I’m trying! Does anyone want to see my invisible rabbit?” “Where is it?” asked a boy. “Exactly.” The magician clapped. “Excellent! My assistant!” “I’m not your assistant,” Bill said. “You are now. Hold this.” He handed Bill the rubber chicken. Bill squeezed it. The chicken shrieked. Every child screamed with delight. Molly froze as a little girl pointed at her sack. “That lady is stealing the presents!” “Amateur,” Bill whispered. Molly stood. “Nonsense. I’m collecting them for safekeeping.” “Why?” “Because,” she said, improvising, “a present goblin is coming.” The children gasped. Bill raised the chicken. “And I’m his terrifying poultry servant.” Molly grabbed his sleeve. “Run.” They bolted toward the gate as children chased them, laughing and throwing party hats. Bill tripped over a balloon, launched himself into the wagon, and crushed the missing wheel. Molly landed beside him. “How many presents?” Bill looked into the sack. “One.” “Which one?” “The robot.” Behind them, Milo shouted, “That’s my favorite!” Molly sighed. “At least we’ve stolen the right thing.” Bill held up the rubber chicken. “And this.” “That wasn’t a present.” “It is now.”
created_at
"2026-07-09T18:13:28.499Z"
7/9/2026, 6:13:28 PM
model
"openai/gpt-5.6-luna-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
491
moderation_latency
(null)
generation_time
4537
tokens_prompt
77
tokens_completion
1097
native_tokens_prompt
66
native_tokens_completion
793
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
0.004824
router
(null)
provider_responses
0
endpoint_id
"eebea444-34a5-4642-a766-cb319471d33a"
id
"resp_05364599a02078f0016a4fe4c8906c8197bd9fe33f695c2ae2"
is_byok
false
latency
269
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-1783620808-QxryuCnWgJllHwmSqeuU"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1783620808-HP5pJNFUfSZ1x9acM8VS"
upstream_id
"resp_05364599a02078f0016a4fe4c8906c8197bd9fe33f695c2ae2"
total_cost
0.004824
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
546
0.12%
Dialogue to Total Word Ratio
Ratio: 58.39%, Deviation: 11.61%
neededClean
false
wordsTotal
548
wordsDialogue
320
0.0594%