NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-09-01KX413NNSNKW3P97HY0HPBPKJ
Run Details
Model:
GPT-5.6 Sol
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
16.6s
Cost:
$0.022320
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
93.65%
Matches word count
(details)
48.28%
Dialogue to Total Word Ratio
(details)
70.9658%
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 the birthday invitation across the café table and pinned its corners with four sugar packets. A cartoon pirate grinned beneath the words CAPTAIN TIMMY TURNS SEVEN. “Fitting,” Bill said. “We’re robbing pirates.” “Children dressed as pirates.” “Pirates are pirates, Molly. Historically, height was not a requirement.” “You’re afraid of children.” “I’m cautious around unpredictable criminals with sticky hands.” Rain ticked against the window. Molly tapped the address printed below a treasure map. The party was scheduled for Saturday at the enormous yellow house belonging to Councillor Pemberton, whose son apparently required thirty guests, a magician, and enough presents to stock a department store. “We enter at three fifteen,” Molly said. “Why not three?” “Cake ceremony. Everyone watches Timmy fail to blow out trick candles.” “Brutal.” “Three ten, the magician releases a dove.” “Indoors?” “Councillor Pemberton has poor judgment and excellent insurance.” Bill studied the invitation. “How did you get this?” “I have sources.” “You stole it from a seven-year-old.” “He dropped it.” “After you bumped into him.” “Gravity committed the crime.” Molly produced a floor plan, two staff badges, and a photograph of the rear entrance. Bill leaned closer, impressed despite himself. The presents would be stored in the conservatory until the treasure hunt ended. Forty boxes, perhaps fifty, guarded by one elderly aunt assigned to stop children opening them early. “What’s our disguise?” he asked. “Entertainment.” “I refuse to be a clown.” “You’re not qualified.” “That sounded personal.” “You’re the magician’s assistant.” Bill recoiled. “The assistant wears sequins.” “You’ll be carrying a clipboard.” “Sequins are implied.” “I’m a party planner. You report an escaped rabbit. Aunt Mildred leaves to help. We load the gifts into catering crates and wheel them out.” “Where’s the real magician?” “Busy.” “What did you do?” “Booked him elsewhere.” Bill narrowed his eyes. “For a retirement home,” Molly added. “That’s almost charitable.” “They think he’s a stripper.” Bill slowly folded the invitation. Outside, a bus sprayed the pavement, drenching a man dressed as a banana. “There’s a flaw,” he said. “Only one?” “These presents belong to children.” “Rich children.” “Still children.” Molly sighed and opened a notebook. Beside each guest’s name was a list of gifts. “We take only the expensive ones,” she said. “Tablets, watches, cash envelopes. We leave toys.” “That is not morally better.” “We replace the valuables with pirate coins.” “Chocolate?” “Gold foil.” Bill considered this. “Children prefer chocolate.” “Exactly.” “And the stolen goods?” “Returned to shops for refunds.” “In cash?” “Mostly.” “So our victims receive chocolate, retailers receive merchandise, and we receive money.” “You’re following.” The waiter approached, and Molly covered the plans with a menu. “Anything else?” he asked. Bill smiled solemnly. “Do you cater children’s parties?” The waiter fled. Molly gathered the papers. “Saturday. Wear black.” “With sequins?” “No sequins.” Bill stood, pocketing three sugar packets. “Then the heist is off.” “Fine. Minimal sequins.” “Now you’re thinking like a professional.” They left the fourth sugar packet pinning Captain Timmy to the table, still grinning, blissfully unaware that his birthday was about to become considerably more chocolatey.
created_at
"2026-07-09T18:09:16.48Z"
7/9/2026, 6:09:16 PM
model
"openai/gpt-5.6-sol-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
559
moderation_latency
(null)
generation_time
16528
tokens_prompt
77
tokens_completion
1075
native_tokens_prompt
66
native_tokens_completion
733
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
0.02232
router
(null)
provider_responses
0
endpoint_id
"a54c5de0-89bf-4ad7-a212-cf977eed918a"
id
"resp_0e63d79a81cd3f9b016a4fe3cc8c4881958c2b635ee6e79346"
is_byok
false
latency
246
model_permaslug
"openai/gpt-5.6-sol-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-1783620556-MU8SF8UWV2cXqmLbrOVh"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1783620556-fzaYAzHrZLF3kleS4XFt"
upstream_id
"resp_0e63d79a81cd3f9b016a4fe3cc8c4881958c2b635ee6e79346"
total_cost
0.02232
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
93.65%
Matches word count
n/a
neededClean
false
words
509
48.28%
Dialogue to Total Word Ratio
Ratio: 53.82%, Deviation: 3.82%
neededClean
false
wordsTotal
511
wordsDialogue
275
70.9658%