NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCXZH21R9KPNCEVBW1N8Q2X
Run Details
Model:
Thinking Machines Inkling (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
8m 13s
Cost:
$0.026669
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
97.63%
Matches word count
(details)
99.99%
Dialogue to Total Word Ratio
(details)
98.8104%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 crumpled blueprint across a picnic table reeking of peanut butter and poor judgment. Her flashlight carved shadows over crayon markings for Sunnybrook Community Center, where a child’s party promised chaos, cake, and a glittering heap of forty-seven wrapped boxes. Bill chewed a stolen granola bar with neurosurgical focus, crumbs raining onto the map like delicious snow. "We go in through the balloon arch," Molly said. Bill frowned. "Timmy has a whistle and asthma?" Molly grinned. "We steal all presents, then vanish." The party began at noon, featuring a magician, three inflatable castles, and parents who believed their children deserved everything. Molly had already blinded the security camera using apple juice and a hair tie. Bill’s duffel held a clown costume with shoes large enough to hide a small car, plus a rubber chicken that served no logical purpose except morale. Bill adjusted his gloves and eyed the exit. Outside, minivans arrived carrying tiny witnesses who still trusted Santa. The heist was technically immoral, structurally absurd, and perfectly timed for the piñata explosion. They would crawl through a gift-table tunnel, abandon the clown nose in a bush, and drive away with every present, leaving behind only confusion, missing scooters, and the faint smell of peanuts.
created_at
"2026-07-25T15:23:26.664Z"
7/25/2026, 3:23:26 PM
model
"thinkingmachines/inkling-20260715"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3435
moderation_latency
(null)
generation_time
492746
tokens_prompt
75
tokens_completion
5653
native_tokens_prompt
75
native_tokens_completion
6573
native_tokens_completion_images
(null)
native_tokens_reasoning
5317
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
0.02666909
router
(null)
provider_responses
0
endpoint_id
"d6b9d68e-115a-49d7-81cd-1ad1c6942b0e"
id
"chatcmpl-RZkyJy62ik64pmvxxQuAJy4M"
is_byok
false
latency
51
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-1784993006-9p9wjSGvAdbJwIXisg95"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784993006-v2eURuI1YYcS5mDIMyQr"
upstream_id
"chatcmpl-RZkyJy62ik64pmvxxQuAJy4M"
total_cost
0.02666909
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
97.63%
Matches word count
n/a
neededClean
false
words
207
99.99%
Dialogue to Total Word Ratio
Ratio: 9.09%, Deviation: 0.91%
neededClean
false
wordsTotal
209
wordsDialogue
19
98.8104%