NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCT8TYM7KZHTWM37V6Y6592
Run Details
Model:
Thinking Machines Inkling (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
2m 27s
Cost:
$0.082201
Provider:
BaseTen
Evaluation summary
Score
Evaluator
Details Link
0.08%
Matches word count
(details)
99.91%
Dialogue to Total Word Ratio
(details)
49.9967%
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 map across the wobbling card table in their storage unit, her marker circling a pastel ranch hosting Timmy's seventh birthday beneath a balloon arch that seemed structurally reckless and possibly flammable. Bill sipped cold coffee beneath a ski mask pushed up like a hairnet of shame, expecting vaults and lasers rather than juice boxes and an unknown face painter. He scanned her annotations—bouncy castle, vague clown, present table sagging with LEGO kingdoms and tablets still in plastic that begged for liberation. "A children's party?" Bill asked, his dignity bruised alongside his pride. Molly ignored him, flipping pages that revealed escape routes avoiding driveways clogged with minivans driven by parents running on caffeine and regret. She wore black with glittering "FUN AUNT" letters, her badge printed on paper smelling of kiosk toner, her laugh now like machinery devouring silverware in thunder. The plan required entering during the magician's finale, stuffing gifts into garbage bags marked supplies, and fleeing before the piñata collapsed and wept candy onto grass. Bill worried that children screamed at frequencies known to shatter glass and resolve, but Molly calculated adequate momentum for one wall-clearing leap. "We strike at cake," Molly said, "when sugar renders everyone useless." Bill tugged on floral oven mitts from a bakery heist gone wrong. "Water balloons mean therapy bills." He pocketed a dinosaur lockpick, resigned to glitter.
created_at
"2026-07-25T14:18:37.407Z"
7/25/2026, 2:18:37 PM
model
"thinkingmachines/inkling-20260715"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
156
moderation_latency
(null)
generation_time
146182
tokens_prompt
75
tokens_completion
18111
native_tokens_prompt
75
native_tokens_completion
20278
native_tokens_completion_images
(null)
native_tokens_reasoning
19974
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
0.0822009
router
(null)
provider_responses
0
endpoint_id
"ba2df08c-c0a0-4e0e-9f31-d79a9c475b70"
id
"chatcmpl-40a6b6b4ad09439ba68bc46acd598225"
is_byok
false
latency
156
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-1784989117-g3mfmK9OA46YjO4x5pkr"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784989117-C0wxDbo7MJafUSyXR3mX"
upstream_id
"chatcmpl-40a6b6b4ad09439ba68bc46acd598225"
total_cost
0.0822009
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
0.08%
Matches word count
n/a
neededClean
false
words
229
99.91%
Dialogue to Total Word Ratio
Ratio: 8.26%, Deviation: 1.74%
neededClean
false
wordsTotal
230
wordsDialogue
19
49.9967%