NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-01-01M1EMNGCGQKEETS7FGTQZBT1N
Run Details
Model:
Thinking Machines Inkling Small (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
17m 27s
Cost:
$0.005541
Provider:
Together
Evaluation summary
Score
Evaluator
Details Link
0.21%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.1070%
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 leaned against the dumpster behind the community center, adjusting her black turtleneck that was definitely not a disguise. "Bill, I told you to wear the clown nose. It’s camouflage." Bill stared at his clipboard, which was a pizza box. "The mom said no clowns. Also, this portfolio is forged." "We're breaking into a children's party to steal presents, not applying for grad school," Molly said. Bill nodded. "Objective: enter, locate gift table, seize packets, exit without being called 'Mr. Magic Man.'" Molly folded her arms. "How do we pass the balloons? Those are psychological warfare." "Easy. I brought cupcakes." Bill produced a plastic tub. "If a kid asks, I say I'm the sugar inspector." "That is unhinged." "Unhinged is how we survive. Did you bring rope?" "I brought rope, duct tape, and How to Talk to Toddlers Without Crying." Bill looked hopeful. "Can we use that?" "No. You distract them with fake magic while I slide under the snack table and lift presents." "You want me to do magic?" "I want you to do anything except actual magic, because I saw you turn that napkin into smoke." Bill adjusted his safety goggles. "My sleight of hand is underrated. I once palmed a goldfish." "It was dead." "It counts. The party starts at two, ends at four. We steal forty gift bags, some with toys that maim small animals." Molly checked her kitchen timer watch. "We go in at two-fifteen, after the pinata." "Why after?" "Decoy. Everyone watches the stick, not the corner gift table." Bill scribbled on the pizza box. "I take the juice station. You take the unicorn flank." "Those look judgmental." "They're soft. My concern is the mother with the headset. She knows everything." "She's just a mom." "If we're caught, we're on a parenting forum forever." Bill sighed at the door where kids screamed about cake. "What if they ask for a gift?" "We give nothing. We are thieves, not Santa." "But it feels wrong." "Moral ambiguity is part of the heist." Bill pulled out a glittery wand. "I have this, just in case." "That is a liability." "Everything is a liability. That's why I have backup." Molly pulled out a small bag of balloons. "I have helium." "Helium is for floating, not crimes." "We can float presents out the window." "Brilliant!" "No, it's stupid, but it confuses them." Bill nodded seriously. "Stay low, stay silent. If anyone asks your name, say you're the balloon artist." "I'm Molly. I steal politely." "Polite theft is best." Molly cracked the door, letting in laughter and frosting. "Remind me why we're doing this." "To buy a boat." "We don't sail." "We just need a boat to store presents." "That makes no sense." "Welcome to heist planning." They stepped inside, the door clicking behind them like the start of something very foolish.
created_at
"2026-09-01T14:06:15.449Z"
9/1/2026, 2:06:15 PM
model
"thinkingmachines/inkling-small-20260730"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4796
moderation_latency
(null)
generation_time
1047343
tokens_prompt
75
tokens_completion
4666
native_tokens_prompt
75
native_tokens_completion
4586
native_tokens_completion_images
(null)
native_tokens_reasoning
3931
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
0.0055407
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788271575-eA14pLxE425dt7FqLi5i"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788271575-NNRMFOFqCSGlfs49RhMN"
upstream_id
"7a18ba88-aws_ue1"
provider_responses
0
endpoint_id
"0ed263b7-f746-4eb6-a14c-54f2e1cc2269"
id
"7a18ba88-aws_ue1"
is_byok
false
latency
4783
model_permaslug
"thinkingmachines/inkling-small-20260730"
provider_name
"Together"
status
200
total_cost
0.0055407
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Together"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
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: 76.11%, Deviation: 26.11%
neededClean
false
wordsTotal
473
wordsDialogue
360
0.1070%