NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCTDJT25JTGM56N4ZZPF968
Run Details
Model:
Thinking Machines Inkling (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
9m 25s
Cost:
$0.030452
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
60.28%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
80.1364%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 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 sequined black turtleneck, which featured dancing snowmen, convinced the festive pattern served as urban camouflage. Bill spread a crayon-map invitation across the dashboard like a classified military blueprint, his expression deeply offended by primary colors. "We hit it during cake," Molly said. "Low risk, high reward present table." Bill tugged his rubber clown nose downward. "It's a kid's party. Not a vault." "Exactly. No cameras. Just Bubbles the dog. We wear these noses, grab gifts, and exit through the bouncy castle." Bill blinked at the inflatable diagram. "Through plastic?" "I deflate it with a hairpin. Classic exit." Bill rubbed his temples, examining a pastel scooter on the list. "We're stealing for Pokemon cards?" "That scooter is four hundred bucks. Choose: rent or dignity." "Dignity pays zero," Bill muttered, accepting the candy-striped duffel. "Nobody suspects clowns with duffels. Avoid the painter—she's ex-military." Molly checked her lockpick, hidden inside a balloon animal kit. Bill stared at his oversized shoes, feeling profoundly undignified. "This is my lowest point." "Your peak was 2019," Molly said, sliding behind the wheel. "Go before they cut the cake and notice every present vanished." Bill sighed, glitter already threatening his leather jacket. "If sparkle gets on me, I kill you." Molly grinned, turning the key. "Let's steal some joy."
created_at
"2026-07-25T14:21:12.906Z"
7/25/2026, 2:21:12 PM
model
"thinkingmachines/inkling-20260715"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
804
moderation_latency
(null)
generation_time
564931
tokens_prompt
75
tokens_completion
6602
native_tokens_prompt
75
native_tokens_completion
7507
native_tokens_completion_images
(null)
native_tokens_reasoning
6241
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
0.03045179
router
(null)
provider_responses
0
endpoint_id
"d6b9d68e-115a-49d7-81cd-1ad1c6942b0e"
id
"chatcmpl-R5Ya6xrFASH2pFKY8x3Naukp"
is_byok
false
latency
59
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-1784989272-l0XAG7J7pRX7bBd88upc"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784989272-C9LUGAti9C139oht8npv"
upstream_id
"chatcmpl-R5Ya6xrFASH2pFKY8x3Naukp"
total_cost
0.03045179
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
60.28%
Matches word count
n/a
neededClean
false
words
215
100.00%
Dialogue to Total Word Ratio
Ratio: 49.31%, Deviation: 0.69%
neededClean
false
wordsTotal
217
wordsDialogue
107
80.1364%