NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCX63FH4FEEB18PR14VMDRR
Run Details
Model:
Thinking Machines Inkling (Reasoning)
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
6m 49s
Cost:
$0.105156
Provider:
Together
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
59.21%
Dialogue to Total Word Ratio
(details)
29.6061%
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 crumpled blueprints across the stolen sedan's hood like she was revealing a lost treasure map. Rain drizzled onto the paper, blurring the garage outline into gray smudges, but she ignored the weather with the serene confidence of a woman who had never once been caught. The suburbs stretched in every direction like a quilt of identical roofs, each one hiding a birthday party that could be robbed by people with enough nerve and poor judgment. She tapped the sliding door with her pen, then turned to Bill, who sat on the curb chewing a toothpick like it had personally offended him. He wore a jacket that had seen better decades. "You're telling me we're robbing a birthday party?" Bill asked. "Themed party," Molly said, smoothing the map. "Six years old. Unicorns. Bouncy castle vomiting toddlers onto the lawn. Parents inside drinking sparkling cider and pretending they're still married." Bill kicked the tire and squinted at the hedge line. "There's an inflatable horse." "Perfect cover. Nobody spots two adults in cargo pants crawling through bushes when there's a rainbow beast throwing up children." Bill adjusted his collar against the drizzle. "You want presents." "Every present. Forty-seven Lego sets. A live pony named Glitterhoof. Resale value that buys us a suspicious retirement." "We don't retire in Belize," Bill said. "We retire in prison." "Then suspiciously wealthy prison. The garage is the party room. Gift table by the sliding door. Child-proof latch. I have a hairpin and emotional damage." Bill looked at the suburban sky, gray and judgmental. "How do we enter?" "We cater. Fairy-tale dress code. Moms wear plastic wings. We wear black, smell like garlic, wheel in an empty cake." "We're not caterers." "We are now. I rented a van that reeks of marinara. We'll wheel out Xboxes and that pony." Bill paused, letting rain soak his hair and his remaining optimism. "There's a pony?" "Shetland. Small. Named Glitterhoof." "You're kidding." "Never about livestock." Bill sighed, long and theatrical. "The kids will scream." "Soundtrack. We'll wear headphones and smile like staff." "You're insane." "I'm entrepreneurial." Molly folded the map with a sharp snap, like she was closing a deal with destiny. "We go in at seven, right when the magician pulls a rabbit out of a hat. While everyone claps, we pull thirty gifts out of the garage. We meet behind the bouncy castle after it deflates." "That castle deflates?" "Soft landing for the pony." Bill shook his head, studying the blueprints as if they might change. "Dumbest plan ever." "Last month I convinced a guard I was a dinosaur expert." Bill almost smiled, despite himself. "That was brilliant." "This is brilliant with balloons." Molly slid behind the wheel of the stolen sedan. "Get in. And lose the toothpick. Caterers don't chew wood." Bill climbed inside, smelling of regret and wet wool. "If caught, I blame you." "If caught, you're a convincing unicorn." "Not a unicorn." "Then you're the caterer with poor attitude and a sack of toys." Bill turned the key. The engine coughed to life with the enthusiasm of a tired horse. "Let's ruin a childhood." "Let's fund our adulthood." The sedan pulled away from the curb, its tires splashing through puddles that reflected the streetlights. They drove toward the suburbs, smelling of garlic, rain, and remarkably poor decisions.
created_at
"2026-07-25T15:09:33.566Z"
7/25/2026, 3:09:33 PM
model
"thinkingmachines/inkling-20260715"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1967
moderation_latency
(null)
generation_time
408418
tokens_prompt
75
tokens_completion
22280
native_tokens_prompt
75
native_tokens_completion
25946
native_tokens_completion_images
(null)
native_tokens_reasoning
25208
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
"stop"
service_tier
(null)
usage
0.1051563
router
(null)
provider_responses
0
endpoint_id
"9911deb9-f44e-4e18-87fe-9d7b60acee72"
id
"otYeU3X-6z2FuN-a20c161d5a6e1157"
is_byok
false
latency
1963
model_permaslug
"thinkingmachines/inkling-20260715"
provider_name
"Together"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer
(null)
request_id
"req-1784992173-2N8KFdEAYdNO4r5eBTKQ"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784992173-TXmVRxOPmQQVJmuoDWBN"
upstream_id
"otYeU3X-6z2FuN-a20c161d5a6e1157"
total_cost
0.1051563
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Together"
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
553
59.21%
Dialogue to Total Word Ratio
Ratio: 53.24%, Deviation: 3.24%
neededClean
false
wordsTotal
556
wordsDialogue
296
29.6061%