NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M37HV8GM0SZHG36G4ZNNZ0V9
Run Details
Model:
GPT-6 Sol
Test:
Dialogue tags
Scenario:
Write 500 words with 30% dialogue
Duration:
14.6s
Cost:
$0.006952
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
0.01%
Matches word count
(details)
7.42%
Dialogue to Total Word Ratio
(details)
3.7140%
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 blueprint across the café table. It was drawn in purple crayon on the back of a dinosaur placemat, but the dimensions were accurate. She had measured the house herself while pretending to sell gutter guards. Bill leaned over it. His elbow landed in a puddle of syrup. “That’s the kitchen,” Molly said. “The party’s in the garden. Presents go in the den, behind this door.” “What’s the squiggle?” “A slide.” “What’s the other squiggle?” “A bigger slide. Focus, Bill.” Bill wiped his elbow with a napkin, which stuck to it. Across the café, a child shrieked with joy at a stack of pancakes. He watched warily. The target was a seventh birthday party on Saturday. Forty guests, two exhausted parents, and an invitation promising a magician. Molly had found it pinned to the café noticeboard beside an offer for piano lessons. “We go in during the magic show,” she said. “Everyone watches the rabbit disappear. We make the presents disappear.” “Do we have a van?” “We have your hatchback.” “It smells like prawns.” “Then nobody will want to inspect it.” Bill considered this. “What if a child sees us?” “We tell them we’re helping.” “Children ask questions.” “Then you answer them.” “That seems like a flaw.” Molly drew an arrow from the den to the side gate. Bill took the crayon and added a small rectangle by the driveway. “What’s that?” she asked. “The birthday cake. We should avoid it. Frosting gets everywhere.” He had once been identified after a burglary by a trail of buttercream. Molly had rescued him by claiming he was delivering a replacement cake, though neither of them had been able to explain why it was in his shoe. At noon on Saturday, they arrived wearing matching polo shirts Molly had found at a charity shop. Both said PARTY HELPERS on the front. Bill’s also said ASK ME ABOUT BALLOONS on the back. The garden was full of children running in loops around a man in a wizard hat. Molly spotted the den through an open window. Beneath a banner that read HAPPY BIRTHDAY, wrapped parcels covered the sofa. “Easy,” she murmured. Bill was immediately handed a bag of balloons by the birthday boy’s father. Molly watched him attempt a knot while she slipped toward the den. A little girl blocked the doorway. “Are you taking the presents?” the girl asked. Molly stopped. “I’m checking they’re all here.” “Good. Mine has a dinosaur sticker.” Molly found it under a gift bag. The girl grinned and followed her back outside, where Bill had inflated one balloon and turned scarlet. The magician called for a volunteer. Every child pointed at Bill. An hour later, the party had acquired thirty balloon animals of uncertain species. Bill’s hands ached. Molly had been put in charge of distributing cake, and the den was now full of parents collecting coats. There was no chance of reaching the presents unseen. As they left, the birthday boy pressed a small parcel into Bill’s hand. “For helping,” he said. In the car, Bill opened it. Inside was a plastic magician’s wand. He tapped the dashboard, hoping the prawn smell might disappear. Nothing happened.
created_at
"2026-09-23T16:33:40.892Z"
9/23/2026, 4:33:40 PM
model
"openai/gpt-6-sol-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2504
moderation_latency
(null)
generation_time
14565
tokens_prompt
75
tokens_completion
843
native_tokens_prompt
66
native_tokens_completion
682
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
0.006952
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790181220-2MXoIQGymzku0rNykfpw"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790181220-oJP27tdEUaSXVtRUckOS"
upstream_id
"resp_059d0c8e0f9a54b0016ab3ff650cf887d1a7ff23ef9fd4c00f"
provider_responses
0
endpoint_id
"1cfc7d9d-4404-4b8e-9ee4-58ae45c9dcd4"
id
"resp_059d0c8e0f9a54b0016ab3ff650cf887d1a7ff23ef9fd4c00f"
is_byok
false
latency
898
model_permaslug
"openai/gpt-6-sol-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.006952
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
0.01%
Matches word count
n/a
neededClean
false
words
531
7.42%
Dialogue to Total Word Ratio
Ratio: 22.79%, Deviation: 7.21%
neededClean
false
wordsTotal
531
wordsDialogue
121
3.7140%