NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCXKVKSZ0JJFWKB4S6HVCZ7
Run Details
Model:
Thinking Machines Inkling (Reasoning)
Test:
Dialogue tags
Scenario:
Write 500 words with 30% dialogue
Duration:
17.3s
Cost:
$0.006632
Provider:
BaseTen
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0000%
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 spread the blueprints across the hood of the borrowed sedan, tapping a red circle around a suburban ranch house. "Party starts at two. That's our window." Bill leaned over, his breath smelling like the gas station burrito he'd regretted since noon. "Kids' parties are loud. Perfect cover." "Exactly. Balloons pop louder than lock picks." Bill squinted at the diagram, which was mostly a napkin with crayon. "How many presents?" "Forty? All wrapped in paper screaming expensive electronics." Bill nodded, adjusting his ski mask, actually a stretched unicorn onesie with the horn sliced off for visibility. "Disguise is key. I go as entertainment." "You're going as what?" "A clown. Edgy. Recently paroled circus performer." Molly rolled her eyes, though her mouth betrayed her. "You're going as our lookout in the bushes." "Bushes? In December? I have delicate sinuses." She pulled a glittery invitation from her pocket, stolen from a mailbox. "Read this. Magical Winter Wonderland for Timmy's Fifth. There's a bouncy castle, Bill." "Wait, there's a bouncy castle?" "Focus. We enter through the sliding door while parents watch a magician pull quarters from toddlers' ears." Bill scratched his chin through the onesie's neck hole. "What if kids see us?" "Kids are short. We'll be ceiling height. Plus sugar crash hits at three-thirty. That's extraction." He pointed at the map's back, a grocery list. "Where's the stash?" "Living room, under a nine-foot artificial pine tree with LED trauma. Bag and tag in ninety seconds." "Ninety? Last job needed ninety seconds to agree on radio channels." "This is precision. You carry the sack—Santa sack, ironic—while I kill the Ring with this magnet." She held up duct-tape wrapped hardware. "Then vanish like ghosts." Bill looked skeptical, then hungry. "What about the dog? Invitation lists Sprinkles, golden retriever." "Sprinkles is diabetic and sleeps through storms. I checked records." "You hacked a vet?" "Bribed a receptionist with scratchers. Details, Bill." He sighed, pulling on fingerless gloves—style, he claimed. "Okay. But if there's a piñata, I'm smashing it. For morale." Molly started the engine, the car coughing like an asthmatic reindeer. "Deal. Fill it with gifts, not candy. Professionals." "Debatable." "In at two-oh-five, out by two-fifteen, richer by LEGO and hoverboards." Bill climbed in, the horn flopping onto the dash. "One condition." "What?" "If Timmy cries, we leave a note. Something nice. Not our real names." "How about The Winter Wraiths?" She pulled into traffic, grinning. "You're an idiot." "And you're missing three hubcaps. Let's rob a birthday." "Seatbelt, horn." "Already flopped. Let's go."
created_at
"2026-07-25T15:17:04.262Z"
7/25/2026, 3:17:04 PM
model
"thinkingmachines/inkling-20260715"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
175
moderation_latency
(null)
generation_time
16516
tokens_prompt
75
tokens_completion
1841
native_tokens_prompt
75
native_tokens_completion
1619
native_tokens_completion_images
(null)
native_tokens_reasoning
994
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
0.00663195
router
(null)
provider_responses
0
endpoint_id
"ba2df08c-c0a0-4e0e-9f31-d79a9c475b70"
id
"chatcmpl-30840f51104f43f0a4c58528db488f08"
is_byok
false
latency
175
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-1784992624-86nHVAZQHS8UjBciOeX7"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784992624-l7U8H3wokz2RqAnEDIXW"
upstream_id
"chatcmpl-30840f51104f43f0a4c58528db488f08"
total_cost
0.00663195
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
421
0.00%
Dialogue to Total Word Ratio
Ratio: 64.87%, Deviation: 34.87%
neededClean
false
wordsTotal
427
wordsDialogue
277
0.0000%