NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCSE6YE7AS6PVBQMYVV5EPR
Run Details
Model:
Thinking Machines Inkling (Reasoning)
Test:
Dialogue tags
Scenario:
Write 500 words with 30% dialogue
Duration:
15.4s
Cost:
$0.007403
Provider:
DeepInfra
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 blueprint across the dashboard of the stolen delivery van, weighing it down with a half-empty bag of cheese puffs. Outside, the suburban cul-de-sac glowed with birthday lights—pink and silver balloons tied to every mailbox like festive surrender flags. "We go in at eighteen hundred hours," Molly said, tapping a crayon circle on the map. "The cake cutting is at eighteen thirty. That gives us a twelve-minute window before the sugar crash hits and the parents start crying." Bill peered over her shoulder, his flashlight illuminating a photograph of a bouncy castle shaped like a dinosaur. "Molly, this is a children's party. There are juice boxes. There are four-year-olds. This feels wrong." "Wrong? Bill, have you seen the haul? We're talking a LEGO Millennium Falcon, a drone, and something called a Squishmallow that's worth forty bucks on the black market. This isn't theft. It's retirement planning." Bill rubbed his temples. "Last week we robbed an art gallery. That was classy. This is... balloons." "Exactly. Nobody suspects balloons. The piñata is our Trojan horse. I stuffed it with sleeping gas—well, lavender essential oil and a little Benadryl I crushed up. When it breaks, everyone takes a nap. Clean, quiet, elegant." "You're going to drug a pony?" "It's a mechanical pony ride. And only if necessary." Bill sighed, adjusting his black turtleneck, which had a stain shaped like Italy. "What about the dog?" "Buster? The golden retriever? I've got a bacon strip soaked in peanut butter. He'll be in the kitchen living his best life." "And the parents?" Molly pulled out a clipboard labeled OPERATION CUPCAKE. "We pose as the entertainment. I'm Princess Sparklehood. You're... the wizard." "I'm not wearing a robe." "Bill, commitment to the bit is what separates professionals from amateurs. You wear the robe, you steal the presents, you don't get caught by a woman named Karen who does Pilates." Bill slumped in the passenger seat. "I just think stealing from children teaches them a bad lesson about capitalism." Molly zipped her tactical backpack. "Bill, capitalism already taught them that by charging thirty dollars for a Squishmallow. We're just correcting the curve. Now put on the pointy hat. The presents aren't going to wrap themselves... wait, they are wrapped. That's the point. Let's go unwrap destiny." She slid the van door open, revealing her costume: a sequined jumpsuit and a tiara that said BIRTHDAY GIRL in glitter. Bill looked at the hat in his lap. "This is the worst heist we've ever planned." "That's why it's going to be the best," Molly said, and stepped into the twilight of the party.
created_at
"2026-07-25T14:04:04.967Z"
7/25/2026, 2:04:04 PM
model
"thinkingmachines/inkling-20260715"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
417
moderation_latency
(null)
generation_time
15117
tokens_prompt
75
tokens_completion
2063
native_tokens_prompt
75
native_tokens_completion
1816
native_tokens_completion_images
(null)
native_tokens_reasoning
1385
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
0.00740324
router
(null)
provider_responses
0
endpoint_id
"d6b9d68e-115a-49d7-81cd-1ad1c6942b0e"
id
"chatcmpl-Rx3RmREpynthZnEV68zk4MXS"
is_byok
false
latency
131
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-1784988245-9GBDVEuIZz1HLvOR6PAe"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784988245-G76hG0gHYBTCjdyoMv9z"
upstream_id
"chatcmpl-Rx3RmREpynthZnEV68zk4MXS"
total_cost
0.00740324
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
0.00%
Matches word count
n/a
neededClean
false
words
436
0.00%
Dialogue to Total Word Ratio
Ratio: 66.74%, Deviation: 36.74%
neededClean
false
wordsTotal
442
wordsDialogue
295
0.0000%