NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-01-01M1EKZ8W90Q7Q9D6J4E250V0Y
Run Details
Model:
Thinking Machines Inkling Small (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
10.5s
Cost:
$0.002439
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 morning light fell through the bakery window like a spilled sugar crust, illuminating the flour dust that settled permanently on the marble counter. A tray of scones cooled near the register, their blueberry tops glistening with a faint, almost sinister sheen. "You’re staring at the pastries like they committed a crime." The librarian lowered her glasses, her finger tapping the glass case in a steady, nervous rhythm. "The berries are wrong. Too dark. And this one—look at the center—someone carved a vanilla bean right into the dough." "That’s elderberry filling, not blueberry. And the bean is streusel." I wiped my hands on the flour-streaked apron, leaving a raspberry smudge across my cuff. "We call it rustic. You’re always weaving murders out of crumbs." "No." She stepped closer, her shadow falling across the tray like a warning. "Initials. M.M. Marigold’s missing since the market robbery. She hasn’t come in since Tuesday." "Could be her initials."
The oven timer chimed
, though no one entered the blue-door shop. "She orders every Tuesday. We still have her usual order in the back." "She hasn’t been seen." Her voice dropped, quieter than the industrial fan’s hum. "What if this is a message?" I leaned over the glass, my breath fogging the surface. The carving wasn’t M.M. It was a tiny, precise M followed by a loop that curled exactly like the bakery’s faded gold monogram, the one stamped on every sign and napkin since my grandmother opened the shop in 1962. "Then the message is for the baker." The bell over the door tinkled. A customer entered, clutching a newspaper, but neither of us turned. Outside, the town clock struck half past seven, and the scent of cinnamon seemed suddenly too sharp, too deliberate.
created_at
"2026-09-01T13:54:06.867Z"
9/1/2026, 1:54:06 PM
model
"thinkingmachines/inkling-small-20260730"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
182
moderation_latency
(null)
generation_time
10378
tokens_prompt
78
tokens_completion
2284
native_tokens_prompt
75
native_tokens_completion
2004
native_tokens_completion_images
(null)
native_tokens_reasoning
1835
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
0.00243855
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788270846-z5RyTUBoSGFlIKDs3JQ9"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788270846-LDileCSIiNRHHBv4AH7O"
upstream_id
"chatcmpl-RqQVKnMMojwhKeKh5cdEbAde"
provider_responses
0
endpoint_id
"d1d9657b-3c3a-49b5-8f81-33204e7c71c3"
id
"chatcmpl-RqQVKnMMojwhKeKh5cdEbAde"
is_byok
false
latency
83
model_permaslug
"thinkingmachines/inkling-small-20260730"
provider_name
"DeepInfra"
status
200
total_cost
0.00243855
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
"The oven timer chimed"