NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-01-01M1ENMSKKPN32PQEAG9SEAD34
Run Details
Model:
Thinking Machines Inkling Small (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
4m 60s
Cost:
$0.013874
Provider:
Together
Evaluation summary
Score
Evaluator
Details Link
90.48%
Matches word count
(details)
91.55%
Dialogue to Total Word Ratio
(details)
91.0190%
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 tapped the glitter-strewn invitation beneath a sagging "Happy Party" banner while Bill adjusted his bowler hat beside juice boxes and a suspicious piƱata. The air smelled of cake and impending chaos. "A children's party, Bill. The security is purely emotional," Molly said. Bill pulled out a crowbar and studied the balloons with professional disdain. "Children are soft targets. They can't clock a con." "We're talking juice and shredded hopes," Molly said, eyeing the entry. "Hope is overrated. I want the dinosaur treasure," Bill replied. "Plan: sneak through the balloon arch. I distract with magic," Molly said. "You do magic?" Bill asked. "Terrible magic. I make a rabbit vanish; the girl cries," Molly said. Bill checked his tool. The bounce house loomed like a plastic castle of doom. "While they weep, I grab gifts?" "Exactly. Fill the duffel, bounce house, gone," Molly said. "What if there's a clown?" Bill asked, glancing at a poster. "Clowns are sad makeup people. I'll ask about feelings," Molly said. Bill smiled. He was clearly not built for childhood celebrations. "This is the worst idea ever." "Good. Let's steal joy," Molly said, pulling on her gloves. They adjusted their masks and stepped toward the balloon arch like professionals who had definitely made better life choices.
created_at
"2026-09-01T14:23:20.698Z"
9/1/2026, 2:23:20 PM
model
"thinkingmachines/inkling-small-20260730"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2706
moderation_latency
(null)
generation_time
299805
tokens_prompt
75
tokens_completion
10126
native_tokens_prompt
75
native_tokens_completion
11530
native_tokens_completion_images
(null)
native_tokens_reasoning
11235
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
0.0138735
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788272600-S6H6DbF5k4Zgs72uT4qy"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788272600-tyzfcH54jDiPKYXMZ3VX"
upstream_id
"2794de7a-aws_ue1"
provider_responses
0
endpoint_id
"faa5ad38-86c9-427e-b1cb-99c43bc4827b"
is_byok
false
latency
47
model_permaslug
"thinkingmachines/inkling-small-20260730"
provider_name
"BaseTen"
status
429
1
endpoint_id
"0ed263b7-f746-4eb6-a14c-54f2e1cc2269"
id
"2794de7a-aws_ue1"
is_byok
false
latency
2705
model_permaslug
"thinkingmachines/inkling-small-20260730"
provider_name
"Together"
status
200
total_cost
0.0138735
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
90.48%
Matches word count
n/a
neededClean
false
words
210
91.55%
Dialogue to Total Word Ratio
Ratio: 44.55%, Deviation: 5.45%
neededClean
false
wordsTotal
211
wordsDialogue
94
91.0190%