NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCWDJ68S4FGSYAEX970F4NY
Run Details
Model:
Thinking Machines Inkling (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
1m 7s
Cost:
$0.045779
Provider:
BaseTen
Evaluation summary
Score
Evaluator
Details Link
75.16%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
37.5778%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 flicked her silver lockpick, letting it spin between her fingers. "Children's birthday party. Pure, uncomplicated profit." Bill nearly dropped his cheap espresso. "You want to rob a room full of five-year-olds?" "Not the kids. The gifts. An Everest of useless plastic garbage." She slapped a crumpled map onto the table. "Saturday at two. Giant bounce house in the yard, parents zombified by sugar." Bill adjusted his glasses. "There's a balloon artist too." "Worse. Camouflage wearing a party hat." Molly smiled like a shark. "We enter as caterers. I wear the hairnet, you push the hollow trolley." "Into a sugar-crazed war zone?" "Precisely. Hidden compartments for loot." Bill rubbed his temples. "My dignity is dead." "Tuesday you wore an otter suit for an aquarium heist." "High art! They revered me!" Molly crammed gear in her bag. "Dress cheerful. No black." "I'm darkness incarnate." "Then be cheerful darkness." She threw a neon vest at him. "Wear it." He caught it like dead fish. "One sticky kid touches me, I flee." "Then carry the bag alone." "How do we escape?" "Back through the bounce house. Adults too tired to notice." Bill studied her. "This is insane." "Insane works." Molly zipped her jacket. "Noon sharp, Bill?" "Yes?" "Cupcakes are safe. The cake is fiberglass. Don't snack."
created_at
"2026-07-25T14:56:09.424Z"
7/25/2026, 2:56:09 PM
model
"thinkingmachines/inkling-20260715"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
199
moderation_latency
(null)
generation_time
66272
tokens_prompt
75
tokens_completion
10243
native_tokens_prompt
75
native_tokens_completion
11285
native_tokens_completion_images
(null)
native_tokens_reasoning
10963
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
0.04577925
router
(null)
provider_responses
0
endpoint_id
"ba2df08c-c0a0-4e0e-9f31-d79a9c475b70"
id
"chatcmpl-0e2daabd4c8d4da78c52e7ab97cf8df4"
is_byok
false
latency
199
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-1784991369-rjbDsN1rdYgbO1xTsIlu"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784991369-GNXA7wI0Ojalo3TEedeQ"
upstream_id
"chatcmpl-0e2daabd4c8d4da78c52e7ab97cf8df4"
total_cost
0.04577925
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
75.16%
Matches word count
n/a
neededClean
false
words
213
0.00%
Dialogue to Total Word Ratio
Ratio: 70.37%, Deviation: 20.37%
neededClean
false
wordsTotal
216
wordsDialogue
152
37.5778%