NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-01-01M1EQ39WESDPYHPNBGZ89XADZ
Run Details
Model:
Thinking Machines Inkling Small (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
1m 41s
Cost:
$0.004134
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0000%
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 drummed her fingers on the Formica table with the rhythm of someone who had already counted every exit in the diner. "Bill, I have executed heists in Frankfurt, Frankfurt-adjacent, and one very confusing mall in Ohio, but breaking into a children's birthday party to steal presents pushes the envelope of my ethical framework." Bill pulled a crumpled napkin from his pocket and smoothed it against his knee. "The invitation says thirty-two guests, ages four to eight, plus a professional entertainer and a bounce house shaped like a shark." "We are not after the shark, Bill." "I thought we were after the shark." "We are after the payload. The shark is a liability." Bill nodded, his mustache twitching. "The parents are in the backyard. There is a garage with a manual door opener that I have already pocketed, though I do not know why." "Because you are confident, which is either charming or fatal." "Both, Molly. Both." Molly stirred her coffee with mechanical precision. "How many presents?" "According to your own reconnaissance, approximately ninety-six, wrapped in foil that reflects sunlight like a signal to the heavens." "We need sunglasses." "We need a bag." "I have a bag." "You have a backpack that says Live Love Laugh on it. That is not intimidating." "I have a duffel." "It is a backpack with delusions." Bill leaned forward. "The presents are arranged near the fireplace in the living room, beside a tree that has lights and therefore a strangling hazard for anyone who is not innocent." "I am never innocent." "You are innocent when you forget to lie." "I never forget." "Then you are unique." They discussed the guard dog, a golden retriever named Bruce who wore a bandana that said Party Patrol. "Bruce is friendly," Molly said. "He knows judo." "He knows treats. We bring treats." "Then he will think we are friends." "Exactly. We are friends who are stealing." Bill checked his watch, which was stopped at three twenty-two, a time that felt symbolic. "Zero hour is three o'clock, when the cake arrives and the parents leave the room." "That gives us thirty minutes to breach the perimeter, avoid the clown, and extract the payload without being pinned by a balloon animal." "There is a clown?" "Professional entertainer. Red nose, oversized shoes, a squeaky voice. I do not trust anyone with a red nose and a positive attitude." "I trust him. He probably cannot run." "We do not rely on speed, Bill. We rely on stealth and bad fashion." "We could use the bounce house." "You are fifty-two years old. You will not fit." "I can deflate." "You do not deflate." "Then we use the garage." "The garage has a door that is very much a door." "We have a manual opener." "I just said that." "Then we are prepared." Molly produced a map drawn on a paper plate. "The window in the bathroom is locked, but I have a hairpin, and you have three hairpins, and between us we have a destiny." "I have a hairpin from the diner." "Then we have four hairpins and a dream." Bill sighed, a sound like a tire deflating. "What is the distraction?" "We pretend to be the entertainment." "We are not entertaining." "We are entertaining ourselves very quietly." "I could wear the clown nose." "That is too conspicuous." "We could cause a moment of confusion." "How?" "By asking about the piñata." "Every child asks about the piñata." "Not with that expression." Molly pointed to the window. "We enter through the bathroom, bypass the kitchen where the juice is, and reach the living room through the hallway that smells like cupcakes." "I love cupcakes." "We do not eat cupcakes. We steal them, perhaps, but as a side mission." Bill pulled out a duffel bag that had been sewn together from several other bags. "The getaway vehicle is a minivan that blends with parents, though I do not have a child." "You have a fake mustache." "That does not make me a parent." "It makes you uncertain." The clock on the wall ticked loudly, or perhaps Bill just imagined it. "We must move," Molly said. "Bill, what is the final plan?" "We walk in. You navigate. I lift. We avoid Bruce, the clown, the bounce house, and any cake with a diamond inside." "Molly, one last thing," Bill said. "Yes?" "The presents are for children." "We are thieves, Bill. We do not split hairs, unless the hair is attached to a hairpin that opens a window." "We do not even split presents." "We split the loot." "We split the loot." "And if you say glitter, I grab the sack." "If you say bounce, I run." "If you say clown, we hide." "If you say cake, I eat a slice." "We do not eat cake." "We are professionals." "Professionals avoid frosting." "Unless it is a code." Then they stood, adjusted their hats, and walked toward the house with the kind of confidence that comes from having nothing to lose except a reputation that was already in ruins.
created_at
"2026-09-01T14:48:44.701Z"
9/1/2026, 2:48:44 PM
model
"thinkingmachines/inkling-small-20260730"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
276
moderation_latency
(null)
generation_time
100402
tokens_prompt
75
tokens_completion
3966
native_tokens_prompt
74
native_tokens_completion
3417
native_tokens_completion_images
(null)
native_tokens_reasoning
2702
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
0.0041337
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788274124-iA4VjxA1SVL9aV8SbSgH"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788274124-eFKUHYNnVb7pWsqwfatX"
upstream_id
"chatcmpl-RWuWDQSc6XvGn1xIBdZT3KFj"
provider_responses
0
endpoint_id
"d1d9657b-3c3a-49b5-8f81-33204e7c71c3"
id
"chatcmpl-RWuWDQSc6XvGn1xIBdZT3KFj"
is_byok
false
latency
97
model_permaslug
"thinkingmachines/inkling-small-20260730"
provider_name
"DeepInfra"
status
200
total_cost
0.0041337
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
841
0.00%
Dialogue to Total Word Ratio
Ratio: 79.67%, Deviation: 29.67%
neededClean
false
wordsTotal
846
wordsDialogue
674
0.0000%