NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M37HJ0SNCTH0RAJ92G3RVPJS
Run Details
Model:
GPT-6 Sol
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
14.9s
Cost:
$0.006772
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
86.38%
Matches word count
(details)
0.82%
Dialogue to Total Word Ratio
(details)
43.5985%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 50% 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 a hand-drawn map across the café table and pinned its corners with sugar packets. It showed a house, a garden, and a rectangle labelled CAKE in red ink. “Where did you get the floor plan?” Bill asked. “From the invitation.” “The invitation has a floor plan?” “It has a picture of the house. I filled in the rest.” Bill studied the map. Between the front door and the cake, Molly had drawn a moat full of teeth. “That’s the family dog,” she said. “The dog’s name is Moat?” “No. Princess Cupcake.” Bill folded his arms. Outside, rain tapped against the window. Inside, Molly’s pencil tapped against a circle marked PRESENTS. She had visited the house earlier, delivering balloons she claimed to have found on a bus. The presents were stacked beside the sofa, and she had counted fourteen so far. A successful job would require a large bag, a distraction, and more nerve than Bill had brought with him. “We go in as entertainers,” Molly said. “Children love entertainers.” “Children love good entertainers. What do we do?” “Magic.” “Can you do magic?” “I can make a fifty-pound note disappear.” “That’s theft.” “It’s the trick we’re planning to do with the presents, scaled up.” Bill looked again at the map. Molly had drawn sixteen stick figures around the cake, each with open jaws. In the margin, she had written AGE SIX and underlined it three times. Bill reached for a sugar packet and set it on the presents. It covered the whole pile. “How do we leave with everything?” he asked. “Through the back gate. I checked the latch.” “While delivering balloons?” “While retrieving one from the garden. Wind is useful.” “And the parents?” “One of us keeps them watching the show. The other carries the bags.” “Which one am I?” “The magician. I’ve seen you shuffle cards.” “I drop them.” “Perfect. They’ll stare at the floor.” A waiter arrived with their tea. Molly slid the map under her saucer, but not before he saw the dog with teeth stretching halfway across the garden. He glanced at Bill. Bill smiled as though he often discussed dangerous pets over breakfast. The waiter put down the cups and left without asking why the word PRESENTS was circled. Bill waited until he was gone. “Have you thought about the birthday child?” “She’s six,” Molly said. “That’s what worries me. Six-year-olds notice things.” Molly pulled the invitation from her pocket. A cartoon unicorn glittered above the words BEA’S BIG DAY. On the back, in smaller writing, Bea’s mother had asked guests not to bring presents. There was no room left in the house. Molly read it twice. Then she turned the map over and began drawing again. “What are you doing?” Bill asked. “Changing the target.” “To what?” “Wrapping paper. They’ll have piles of it after cake.” Bill lifted his cup. “Nobody will pay for stolen wrapping paper.” Molly looked up. “Who said anything about paying? Bea’s mother needs a hand cleaning up.” Bill considered the dog. “We’d better bring biscuits for Princess Cupcake.”
created_at
"2026-09-23T16:28:38.076Z"
9/23/2026, 4:28:38 PM
model
"openai/gpt-6-sol-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2488
moderation_latency
(null)
generation_time
14878
tokens_prompt
75
tokens_completion
839
native_tokens_prompt
66
native_tokens_completion
664
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
0.006772
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790180918-zqNN7GPINxWDZLJ9kZfD"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790180918-3t6GvYaWwDF51aj840cB"
upstream_id
"resp_03b4dd46badc6a9e016ab3fe3634fc87d187879f947187048e"
provider_responses
0
endpoint_id
"1cfc7d9d-4404-4b8e-9ee4-58ae45c9dcd4"
id
"resp_03b4dd46badc6a9e016ab3fe3634fc87d187879f947187048e"
is_byok
false
latency
879
model_permaslug
"openai/gpt-6-sol-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.006772
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
86.38%
Matches word count
n/a
neededClean
false
words
511
0.82%
Dialogue to Total Word Ratio
Ratio: 40.19%, Deviation: 9.81%
neededClean
false
wordsTotal
515
wordsDialogue
207
43.5985%