NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCW1PD4ECVEYVRHGZWFPW45
Run Details
Model:
Thinking Machines Inkling (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
2m 55s
Cost:
$0.106124
Provider:
BaseTen
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
99.90%
Dialogue to Total Word Ratio
(details)
49.9511%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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 said, "Bill, we're hitting a six-year-old's blowout at Maple Center. Thirty sugar-crazed kids, each hauling wrapped gifts—consoles, scooters, maybe a live parrot." Bill said, "I trained for high-security vaults with biometric lasers, not germ-ridden ball pits with questionable morality and worse lighting." Molly said, "We wear full clown regalia with neon wigs, cracked face paint, and shoes that squeak like tortured rodents. Balloons hide our faces and our felony intent." Bill said, "In 2009 a balloon poodle psychologically destroyed me at a county fair, leaving therapist bills and recurring latex nightmares." Molly said, "Parents perform drive-by drop-offs then flee for overpriced espresso, leaving us with a mound of gifts hidden among streamers and regret." Bill said, "You're seriously proposing we steal from actual children, those sticky emotional creatures with questionable reasoning and loud voices?" Molly said, "While they violently bludgeon a papier-mâché donkey with baseball bats, we professionally bludgeon the coat check with our duffel." Bill said, "What if they notice strangers leaving? What if they weep? I once sobbed uncontrollably for twenty minutes during a softness detergent commercial." Molly said, "Then we invoke the Phantom Magician, blaming an entertainer who was never actually booked. By then we're three counties away cataloging merchandise." Bill said, "There's only two of us, so arithmetic is aggressively incriminating! This violates ethics, SpudCoin was avant-garde art, giraffes have dead eyes, and I'm absolutely hellbound with presents!"
created_at
"2026-07-25T14:49:40.528Z"
7/25/2026, 2:49:40 PM
model
"thinkingmachines/inkling-20260715"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
112
moderation_latency
(null)
generation_time
173982
tokens_prompt
75
tokens_completion
21814
native_tokens_prompt
75
native_tokens_completion
26185
native_tokens_completion_images
(null)
native_tokens_reasoning
25841
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
0.10612425
router
(null)
provider_responses
0
endpoint_id
"ba2df08c-c0a0-4e0e-9f31-d79a9c475b70"
id
"chatcmpl-eced883001ec4d52bbf929f008b5a40b"
is_byok
false
latency
112
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-1784990980-Jx4FyqQlRwg69w6zC0HO"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784990980-2PGz81wu4Kc38vUgWn2g"
upstream_id
"chatcmpl-eced883001ec4d52bbf929f008b5a40b"
total_cost
0.10612425
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
0.00%
Matches word count
n/a
neededClean
false
words
234
99.90%
Dialogue to Total Word Ratio
Ratio: 91.77%, Deviation: 1.77%
neededClean
false
wordsTotal
243
wordsDialogue
223
49.9511%