NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCXNW6DSJNAV9E67Q5R1EHD
Run Details
Model:
Thinking Machines Inkling
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
10.3s
Cost:
$0.002673
Provider:
Together
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 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
"Bill, this is the worst idea you have ever burped into existence," Molly said. "Burped? That was refined criminal thinking with carbonation." "We are breaking into a children's party to steal presents. Do you hear yourself?" "Every present in that bouncy castle belongs to us by midnight." "There is not a bouncy castle with a vault." "There will be when I inflate the decoy with stolen air." "We do not own an air pump." "That is what lungs are for, Molly. Dedication." "You are going to hyperventilate over a pile of wrapped cardboard." "I have trained for this. I once held my breath through an entire flute recital." "That was your own sister's wedding." "Still counts." Molly kicked the tire of the van. "Walk me through the entry strategy without saying the word bounce." "We wait until the magician pulls the rabbit from the hat. Classic misdirection." "The rabbit is made of foam." "Then we steal the hat too. Double score." "Bill, children will be present. Small ones. Loud ones. Sticky ones." "Sticky ones are easier to track. They leave evidence." "We are not tracking them. We are robbing them." "Semantics. Look, we wear disguises." "You bought a neon dinosaur onesie." "It has pockets." "For what? Snatched party favors?" "Exactly. You understand the vision now." "I understand that if we get caught, I will blame you in every language I pretend to speak." "Noted. I also bought matching onesies for the getaway driver." "We do not have a getaway driver." "We do now. I called Gary." "Gary still owes you fifty dollars and a sandwich." "He works for sandwiches." Molly rubbed her temples. "What about the alarms?" "Disabled. I unplugged the birthday candles." "Those are not alarms, Bill." "Then we are already inside the perimeter of success." "The presents are wrapped in glitter paper and hope. How do we transport forty-seven boxes?" "Forty-seven? Did you count?" "I did reconnaissance. There are forty-seven gifts stacked like a glittering pyramid of regret." "Then we need a bigger sack." "You brought a laundry hamper." "You said bring a sack. This is a sack with ventilation." "We are going to prison with laundry." "If prison has bouncy castles, I am ready." Molly sighed. "What is the signal if things go wrong?" "If I scream like a balloon releasing air, you leave me." "That is your signal every Tuesday." "Consistency is the backbone of crime." "And poor impulse control is its skull." "Poetic. Are we partners or poets?" "We are fools with matching dinosaur pockets." "Then let us steal some joy and run." "Promise me one thing." "Anything except quitting." "If a child offers me juice, I am allowed to take it." "Only if you share." "Deal." Bill adjusted his onesie hood with ceremonial gravity. "Molly, tonight we become legends in neon green scales." "Tonight we become headlines in local police reports." "Same thing, different font."
created_at
"2026-07-25T15:18:10.388Z"
7/25/2026, 3:18:10 PM
model
"thinkingmachines/inkling-20260715"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
161
moderation_latency
(null)
generation_time
7585
tokens_prompt
75
tokens_completion
760
native_tokens_prompt
73
native_tokens_completion
642
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
0.0026731
router
(null)
provider_responses
0
endpoint_id
"9911deb9-f44e-4e18-87fe-9d7b60acee72"
id
"otYh8RA-6z2FuN-a20c22c8492bad1a"
is_byok
false
latency
157
model_permaslug
"thinkingmachines/inkling-20260715"
provider_name
"Together"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer
(null)
request_id
"req-1784992692-jrmhRShc8mIEDVV0bBAq"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784992692-i6mBTirDME6FVqW3Jiff"
upstream_id
"otYh8RA-6z2FuN-a20c22c8492bad1a"
total_cost
0.0026731
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Together"
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
481
0.00%
Dialogue to Total Word Ratio
Ratio: 95.25%, Deviation: 45.25%
neededClean
false
wordsTotal
484
wordsDialogue
461
13.5829%