NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-01-01M1ENN6VETS9JY9K6SGTCVBXN
Run Details
Model:
Thinking Machines Inkling Small (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
19.8s
Cost:
$0.003164
Provider:
Together
Evaluation summary
Score
Evaluator
Details Link
100.00%
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 bell above the door jangled, releasing a gust of autumn air and wet pine. "You stayed past closing again." "I was trying to prove you have a second flour sifter." "I have one sifter and one life, and a health inspector due by ten." A tin tray clattered against the marble counter. The baker wiped her hands across her apron, leaving a streak of cinnamon. "Then stop tracking mud everywhere and tell me why you really came." "I want a croissant." "You want answers." The customer leaned in, lowering his voice. "The coroner's report mentioned almond extract. The same bottle that sits on your top shelf." She turned slowly, eyes narrowing. "Are you accusing me of something?" "I'm asking if the bottle on your shelf matches the one from Mrs. Halloway's kitchen." "Why would her extract be here?" "Because someone swapped them. And because you were the last person seen at her door yesterday morning." She reached for a knife, clicking it against the cutting board with deliberate precision. "I was delivering a dozen blueberry scones." "Your receipt timestamp says seven-thirty. The neighbor says you left at eight-fifteen." "I stay late because people like you keep circling back." The blade paused above a brioche. "If you think I poisoned anyone, check my gloves. They're still clean." "Then why does your apron smell like bitter almonds?" She stared at him, flour dust settling between them like snow. "Because I use them in everything, Jude. Just like everyone else in this town." "That doesn't mean you didn't know the difference." A scone rose in the oven behind her, golden and innocent, and for a moment the only sound was the hiss of steam. "Buy something, detective. Or leave me with my guilt and my pastries."
created_at
"2026-09-01T14:23:34.262Z"
9/1/2026, 2:23:34 PM
model
"thinkingmachines/inkling-small-20260730"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
290
moderation_latency
(null)
generation_time
19749
tokens_prompt
78
tokens_completion
3086
native_tokens_prompt
76
native_tokens_completion
2605
native_tokens_completion_images
(null)
native_tokens_reasoning
2227
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
0.003164
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788272614-PDImJznheOZaOC44BzRn"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788272614-5iprFh3DCz6jwEHzZGvv"
upstream_id
"84d119b7-aws_ue1"
provider_responses
0
endpoint_id
"0ed263b7-f746-4eb6-a14c-54f2e1cc2269"
id
"84d119b7-aws_ue1"
is_byok
false
latency
290
model_permaslug
"thinkingmachines/inkling-small-20260730"
provider_name
"Together"
status
200
total_cost
0.003164
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Together"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)