NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-01-01M1EM66J96418KN2RK8GB6564
Run Details
Model:
Thinking Machines Inkling Small (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
1m 32s
Cost:
$0.010113
Provider:
Together
Evaluation summary
Score
Evaluator
Details Link
14.30%
Matches word count
(details)
99.99%
Dialogue to Total Word Ratio
(details)
57.1451%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 adjusted her ski mask and squinted at the inflatable slide dominating the backyard. "Bill, security is a juice box," she whispered, clutching her pillowcase duffel of stolen menus. Bill nodded, clipboard in hand, wearing black gloves made from stolen oven mitts. "Standard protocol: hit the piƱata." They crouched behind hydrangeas, eyeing the glittering mountain of wrapped toys beneath the oak tree. The backyard smelled like sugar and regret. Molly pulled out a grappling hook fashioned from licorice rope. The party started in five minutes, which meant open season on small plastic dinosaurs and overpriced action figures wrapped in metallic paper that reflected the sun. Bill scratched his chin. Molly said they should take cupcakes too, and that gift hierarchy meant presents first, sugar second, emotional growth never. They scaled the fence, landing softly among discarded balloon animals and crushed juice boxes. A shriek pierced the air about pinning tails, but Molly yanked Bill toward the treasure trove. "Quick, before they sing." Bill snatched a silver-wrapped toy car with the satisfied grin of a man achieving his lifelong dream. Molly stuffed a remote-controlled car into her sack. "One more and we're gone." A red balloon popped with a sound like a dying trumpet. They bolted down the sidewalk, leaving only glitter and one very confused child staring at an empty table.
created_at
"2026-09-01T13:57:53.873Z"
9/1/2026, 1:57:53 PM
model
"thinkingmachines/inkling-small-20260730"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
157
moderation_latency
(null)
generation_time
92023
tokens_prompt
75
tokens_completion
7440
native_tokens_prompt
75
native_tokens_completion
8396
native_tokens_completion_images
(null)
native_tokens_reasoning
8105
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
0.0101127
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788271073-MOZUdlqx77hIwYQUgRCH"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788271073-9BuVpwi3sKn5fxM9u2x9"
upstream_id
"5ccef911-aws_ue1"
provider_responses
0
endpoint_id
"0ed263b7-f746-4eb6-a14c-54f2e1cc2269"
id
"5ccef911-aws_ue1"
is_byok
false
latency
151
model_permaslug
"thinkingmachines/inkling-small-20260730"
provider_name
"Together"
status
200
total_cost
0.0101127
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
14.30%
Matches word count
n/a
neededClean
false
words
221
99.99%
Dialogue to Total Word Ratio
Ratio: 8.97%, Deviation: 1.03%
neededClean
false
wordsTotal
223
wordsDialogue
20
57.1451%