NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-01-01M1EMJNMQDK965295AX25QKCK
Run Details
Model:
Thinking Machines Inkling Small (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
22.6s
Cost:
$0.004209
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
60.65%
Count dialogue tags
(details)
Model input
User/Human
You are an expert novel writer in the cozy mystery genre. Write a scene of about 200 words, with dialogue between two characters. The dialogue should be unattributed, meaning the speaker is not explicitly mentioned. The scene should be set in a small town bakery. Only return the story, nothing else.
Model response
Messages
Meta
AI
The scent of proofing dough and burnt caramel clung to the linen curtains as Clara wiped the counter, her apron dusted with flour. The door chime rang. Rowan stepped inside, clutching a folded newspaper. "You missed yesterday's batch." Clara turned, hands on her hips. "Library archives. Had to verify the mill deed." Rowan slid the paper across the counter. "Page four. Arthur Pendelton's obituary." She leaned in, reading the small print. "The mill owner?" "Exactly. Someone emptied his safe last night." Rowan tapped the photo of Arthur's grin. "Your sourdough starter was inside it." Clara's breath caught. "The recipe he gave me in 1987?" "Untouched for thirty years." Rowan glanced at the open flour bin. "Then I saw this." A muddy tread, clearly male, pressed deep into the white dust. "Who wants old yeast?" Clara stared at the footprint. Rowan smiled. "Bake, and we'll see who comes sniffing." She grabbed her mixing bowl. "You take the front counter. I'll handle the back oven." "Cozy mystery solved by sugar?" "Cozy mystery solved by fermentation,"
she corrected
. Rowan leaned against the counter, arms folded. "The footprint matches boots from the hardware store." Clara paused, spoon in hand. "Meaning our suspect didn't just steal the safe. He wanted the proof." "Exactly." Rowan pointed to the oven. "Start mixing. The real detective work happens behind the flour." The oven timer dinged. Clara opened the drawer for the starter. "If this is ruined, I'm blaming Arthur." Rowan nodded. "Good. The best clues always rise."
created_at
"2026-09-01T14:04:42.528Z"
9/1/2026, 2:04:42 PM
model
"thinkingmachines/inkling-small-20260730"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
299
moderation_latency
(null)
generation_time
22566
tokens_prompt
78
tokens_completion
3829
native_tokens_prompt
75
native_tokens_completion
3479
native_tokens_completion_images
(null)
native_tokens_reasoning
3429
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
0.00420855
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788271482-hK7QMw7OujMXDs1Pncba"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788271482-g3ePiA742MIH6Jc547EI"
upstream_id
"chatcmpl-RmJHKWwXllZhW6mtcTtoyTu1"
provider_responses
0
endpoint_id
"d1d9657b-3c3a-49b5-8f81-33204e7c71c3"
id
"chatcmpl-RmJHKWwXllZhW6mtcTtoyTu1"
is_byok
false
latency
184
model_permaslug
"thinkingmachines/inkling-small-20260730"
provider_name
"DeepInfra"
status
200
total_cost
0.00420855
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
60.65%
Count dialogue tags
n/a
neededClean
false
dialogueTags
0
"she corrected"