NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCWS3KZXS9S02HS0RD032JQ
Run Details
Model:
Thinking Machines Inkling
Test:
Dialogue tags
Scenario:
Write 500 words with 30% dialogue
Duration:
7.8s
Cost:
$0.002819
Provider:
BaseTen
Evaluation summary
Score
Evaluator
Details Link
27.17%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
13.5829%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 30% 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 shoved her black beanie over her ears and leaned closer to Bill. "This is the worst idea you have ever had, and you once tried to rob a pet store using only a laser pointer." Bill spread a crumpled map across the hood of his stolen sedan. "It is genius. Thirty kids, one living room, presents stacked like a pyramid of poor financial decisions." "Children will scream." "Children always scream. That is biological." Molly pointed at a crayon circle on the map. "That is the snack table. Cheese puffs are not cover for us." "We dress like entertainers. I wear the balloon hat, you carry the guitar case with the actual loot inside." "You do not play guitar." "I do not need to play it. I need to hide inside it." Molly rubbed her temples. "We are breaking into a birthday party for a six-year-old." "Exactly. Six-year-olds have no security instincts." "They have parents." "Drunk on punch and distracted by a magician who pulls quarters from ears." Molly circled the car, pacing. "What if there is a dog?" "There is always a dog in these neighborhoods. We bring bacon." "We are thieves, not caterers." Bill folded the map with theatrical precision. "Molly, think about the haul. Video games, plastic dinosaurs, remote control cars that cost more than our rent." "Rent is late because you bought a jet ski." "That was an investment." "In a lake town with no lakes." Bill ignored her and pulled out two neon vests from the trunk. "These say Party Patrol. I made them in the dark with a Sharpie." Molly read the crooked letters. "That says Party Potato." "Same energy." She sighed, long and suffering, like a woman who had made many poor life choices that all led back to this parking lot. "We need a distraction." "We are the distraction. You sing Happy Birthday off-key while I crawl behind the sofa." "I cannot sing." "You can scream-sing. That works." Molly stopped pacing and fixed him with a stare. "If we get caught, I am blaming you in court." "Deal. And if we succeed, I am keeping the jet ski." "There is no jet ski." "There will be. After we fence the goods." She grabbed the vest and pulled it over her hoodie. "What about the presents being wrapped? We do not have time to unwrap thirty boxes." "We do not unwrap. We take the boxes, sell them wrapped on the secondary market. Mystery gifts. People love mystery." "That is just shipping other people's garbage." "Child garbage is premium garbage." Molly checked her watch, then her pockets for lockpicks she already knew were there. "We go in at cake time. Sugar crashes create blind spots." "Brilliant." "Not brilliant. Surviving." Bill grinned and zipped his jacket. "Same thing, partner." She opened the car door with a resigned groan. "If there is a clown, I am leaving you inside." "Noted. Clowns are your problem." They walked toward the glowing house with its balloons tied to every railing, two terrible people in terrible vests, carrying a guitar case full of nothing but confidence and poor judgment.
created_at
"2026-07-25T15:02:27.722Z"
7/25/2026, 3:02:27 PM
model
"thinkingmachines/inkling-20260715"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
155
moderation_latency
(null)
generation_time
7171
tokens_prompt
75
tokens_completion
774
native_tokens_prompt
73
native_tokens_completion
678
native_tokens_completion_images
(null)
native_tokens_reasoning
0
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
0.0028189
router
(null)
provider_responses
0
endpoint_id
"ba2df08c-c0a0-4e0e-9f31-d79a9c475b70"
id
"chatcmpl-b82d1b054e1649eb882cd537bf833e9f"
is_byok
false
latency
155
model_permaslug
"thinkingmachines/inkling-20260715"
provider_name
"BaseTen"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer
(null)
request_id
"req-1784991747-B49HqsGCls41J5O1ruj0"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784991747-2hvOmQZ3095m47izdhsy"
upstream_id
"chatcmpl-b82d1b054e1649eb882cd537bf833e9f"
total_cost
0.0028189
cache_discount
(null)
upstream_inference_cost
0
provider_name
"BaseTen"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
27.17%
Matches word count
n/a
neededClean
false
words
519
0.00%
Dialogue to Total Word Ratio
Ratio: 67.81%, Deviation: 37.81%
neededClean
false
wordsTotal
525
wordsDialogue
356
13.5829%