NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCVH95WK0A1CVNQ2FJPCPBC
Run Details
Model:
Thinking Machines Inkling (Reasoning)
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
7m 23s
Cost:
$0.021129
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
0.21%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.1071%
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 adjusted her black balaclava in the rearview mirror of the stolen panel van, which smelled like wet dog and regret. Rain turned the street into a soup of minivans and balloons tied to mailboxes. "The birthday boy turns six tomorrow," she said. "That means Lego with nine hundred pieces, a scooter, probably a giant stuffed giraffe that costs more than my rent." Bill was eating a burrito over a blueprint. "We hit after cake but before the magician pulls a quarter from Timmy's ear. Classic window." "You want to rob a child during his magic window?" "I want to rob a child during his sugar crash window. There's a difference." Molly pointed at the blueprint. "There's a bounce house inside. You can't stealth through that." "Who said stealth? I'm going in as the entertainment." He pulled a crushed collapsible top hat from his duffel. "Ta-da. Emotionally intact." "We're stealing presents from a first-grader. Have you lost your moral compass?" "My compass points to resale value. Those scooters are three hundred bucks. The Lego? Retired sets go for gold." "It's not the dark web if you sell on Facebook Marketplace, Bill." "Dark Facebook, then." She pulled on gloves. "Entry point? The front door's guarded by a grandmother with a camera doorbell and a shotgun named Betsy." "Side gate by the garage. The dad's a barbecue guy. Always unlocked because he thinks he's Tom Brady of propane." "Alarm?" "Disabled twenty minutes ago with my charm and a forged pool coupon." "You forged a pool coupon?" "First Clean Free. I cleaned nothing. Gained access." "That is not how pool coupons work." "It's how mine work." She grabbed the duffel. "We have forty minutes before dinosaur cake. Extraction?" "Same van, different plates. Garbage bags that say Happy Birthday in glitter. We blend with trash." "We're stealing gifts in birthday garbage bags?" "It's thematic. If stopped, we cry and say we're returning unwanted socks." Molly opened the door. Rain hit her face. "Bill, if we get caught, I'm blaming the burrito." "The burrito believes in us." They crossed the lawn, dodging a flamingo lawn ornament in a party hat. The house glowed pink and blue. Inside, children screamed with joy—excellent cover noise. "Remember," Bill whispered, fixing his hat, "in and out. No talking to kids. No cake. No bouncing." "I'm not bouncing. I'm a professional." "Then why are you smiling?" "That's my robbery face." "It looks like you're enjoying this." "Shut up and open the gate." The gate creaked. Bill held up a finger. "Hear that? Capitalism failing." "That's you stepping on a squeaky duck." "See? Already blending in." Molly slipped inside, wondering when her life became a cartoon. Behind her, Bill saluted a plastic T-Rex. The heist had begun. Somewhere inside, a six-year-old was about to learn magic wasn't real—but theft certainly was.
created_at
"2026-07-25T14:40:42.694Z"
7/25/2026, 2:40:42 PM
model
"thinkingmachines/inkling-20260715"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
960
moderation_latency
(null)
generation_time
442632
tokens_prompt
75
tokens_completion
5710
native_tokens_prompt
75
native_tokens_completion
5205
native_tokens_completion_images
(null)
native_tokens_reasoning
4974
native_tokens_cached
32
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
0.02112869
router
(null)
provider_responses
0
endpoint_id
"d6b9d68e-115a-49d7-81cd-1ad1c6942b0e"
id
"chatcmpl-RAgoLtHNzDcxfbVSje3S8yQN"
is_byok
false
latency
69
model_permaslug
"thinkingmachines/inkling-20260715"
provider_name
"DeepInfra"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer
(null)
request_id
"req-1784990442-jtuXzfWGhBFJ8adTxxgn"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784990442-DM4hERWoSWW99v1MPgFN"
upstream_id
"chatcmpl-RAgoLtHNzDcxfbVSje3S8yQN"
total_cost
0.02112869
cache_discount
0.00002656
upstream_inference_cost
0
provider_name
"DeepInfra"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
0.21%
Matches word count
n/a
neededClean
false
words
472
0.00%
Dialogue to Total Word Ratio
Ratio: 67.65%, Deviation: 17.65%
neededClean
false
wordsTotal
476
wordsDialogue
322
0.1071%