NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-01-01M1EN2E9A45SVDY7CREKH602X
Run Details
Model:
Thinking Machines Inkling Small (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
33.3s
Cost:
$0.002826
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
99.86%
Dialogue to Total Word Ratio
(details)
49.9282%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 70% 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 leaned against the diner booth and stared at Bill with the kind of disappointment reserved for men who had already made terrible choices. “Bill, have you considered that a children’s birthday party is basically Fort Knox with juice boxes and a bounce house?” Bill adjusted his cap and smiled with the confidence of a man who had never faced a piñata. “Fort Knox doesn’t have a balloon arch, Molly. And that’s exactly why we’re in. Security is asleep because they’re eating cupcakes shaped like animals.” “We’re going to steal presents from eight-year-olds?” “It’s not stealing if they never unwrapped them,” Bill said, sliding a napkin across the table. “It’s redistribution. I’m taking from the rich—well, middle-class parents with a rented dinosaur slide.” Molly crossed her arms. “The dinosaur slide is the problem. I cannot dodge a slide and a clown with a rubber chicken at the same time.” “Leave the clown to me. I’m bringing a wrench and a fake mustache.” “A fake mustache? You look like a substitute teacher who lost a bet with a leprechaun.” “It’s a disguise,” Bill insisted. “Nobody suspects a man with a mustache and a wrench. Especially not kids who are already stuffing their faces with pizza rolls and false hope.” Molly sighed loudly. “What about the presents? They’re under the table, behind the cake, inside a tent clearly labeled ‘No Trespassing Except by Children and Santa.’” “Santa doesn’t exist, Molly. That’s the whole point of the heist. We enter as Santa.” “You don’t have a belly.” “I have a vest and a lie,” Bill said, producing a crumpled red string vest from his coat. “And I have a plan. We arrive at four-fifty, when the parents are drunk on sparkling cider and singing badly. We climb the fence using the inflatable dinosaur. We sweet-talk the clown—wait, no clown, we avoid the clown—then we grab the presents.” “The clown is armed.” “With a rubber chicken,” Molly agreed. “Which is terrifying,” Bill said. “Exactly. Psychological warfare.” Molly rolled her eyes. “I’ll handle the presents. You handle the clown. But what if they have a security guard?” “There’s a six-year-old with a bubble wand.” “Not helpful.” “Then we use the bubble wand. I have a blueprint.” Bill pulled out a folded map of a suburban cul-de-sac. “The party is at 442 Spriggan Lane. Starts at three. We enter at three-fifteen because that’s when the cake is cut and everyone is staring at the candles like they owe them money.” “That’s genius,” Molly said, “and also terrifying.” “It’s logistics,” Bill corrected. Molly tapped the table. “What about the presents themselves? There’s going to be Legos, a dollhouse, and something that beeps when you press a button. I don’t want to carry a noisy toy out while sneaking past a bounce house.” “We switch them,” Bill said, opening a duffel bag to reveal neatly folded socks. “I bring a bag of socks. We swap presents for socks. The kids won’t know until they open them in front of their parents.” “That’s diabolical.” “It’s charitable,” Bill said. “We’re giving them socks.” “You’re giving them disappointment.” Bill smiled. “Exactly. The true heist isn’t just stealing gifts—it’s teaching children about life and lower expectations.” Molly frowned. “Bill, I think your heart is in the wrong place, and your hat is on too tight.” “No, my heart is in the right place, but my stomach is in the wrong place. I haven’t eaten since this morning and I smell like a fake mustache.” “We can steal pizza rolls too?” “Only if they’re wrapped,” Bill said. Molly checked her watch. “We have forty minutes to case the place. I’m driving.” “Of course you’re driving. You always drive because you have a truck.” “I have a truck and a conscience.” “You have a truck and a fear of balloons,” Bill said. “That’s not fear, Bill. That’s strategy.” Bill stood and adjusted the red vest over his shirt. “Let’s go. We enter as Santa, leave as legends, and if anyone asks, we say we were delivering presents that someone else stole first.” “That makes no logical sense.” “It doesn’t need to. It’s a children’s party. Nobody’s paying attention anyway.” Molly followed him out to the parking lot, where a single truck idled with the kind of hope that usually ends in documentaries. She started the engine. “Did you bring the wrench?” “Yes.” “And the mustache?” “It’s already on,” Bill said, pointing to his face. “Molly,” he continued, “that’s your actual face.” “I don’t have a real mustache,” Molly said. “Then I’m prepared,” Bill announced. Molly drove toward the neighborhood, where balloons already swayed in the breeze like the last wishes of a doomed republic. “This is the worst idea I’ve had all week,” she said. “Then we must be ready,” Bill replied. The party loomed. Parents laughed. A clown adjusted a rubber chicken. And somewhere inside, a pile of presents waited, innocent and shiny, unaware that two thieves with a vest and a grievance were coming to teach them about socks. Bill whispered, “To glory, Molly.” She whispered back, “To socks.” The truck turned onto Spriggan Lane, and the heist began in the only way it could—badly, loudly, and with a very suspicious chest.
created_at
"2026-09-01T14:13:19.282Z"
9/1/2026, 2:13:19 PM
model
"thinkingmachines/inkling-small-20260730"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
192
moderation_latency
(null)
generation_time
33258
tokens_prompt
75
tokens_completion
2770
native_tokens_prompt
74
native_tokens_completion
2327
native_tokens_completion_images
(null)
native_tokens_reasoning
1321
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
0.0028257
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788271999-kwPWKCHoxLlBFJ8iQofa"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788271999-rARO0XURuyDxtXwAg0eg"
upstream_id
"chatcmpl-RKOmV2OuLTvpsSXYAFwU6NqC"
provider_responses
0
endpoint_id
"d1d9657b-3c3a-49b5-8f81-33204e7c71c3"
id
"chatcmpl-RKOmV2OuLTvpsSXYAFwU6NqC"
is_byok
false
latency
79
model_permaslug
"thinkingmachines/inkling-small-20260730"
provider_name
"DeepInfra"
status
200
total_cost
0.0028257
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
875
99.86%
Dialogue to Total Word Ratio
Ratio: 70.17%, Deviation: 0.17%
neededClean
false
wordsTotal
885
wordsDialogue
621
49.9282%