NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-01-01M1EM4ZMTB7NJ1CXYZYV1AK0P
Run Details
Model:
Thinking Machines Inkling Small (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
57.6s
Cost:
$0.014420
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
27.17%
Matches word count
(details)
20.88%
Dialogue to Total Word Ratio
(details)
24.0233%
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 adjusted her black gloves beneath the flickering neon birthday banner and pointed at the inflatable castle. "Bill, every present is trapped behind the superhero cake." Bill squinted through the hydrangea hedge, clutching a stolen invitation. "I count twelve children, forty juice boxes, and one clown wearing a silent alarm on his forehead." "Clown is a decoy," Molly whispered, adjusting her hair clip. "The real security is that mother with the laser stare. We enter through the sandbox." "We have no ladder." "We have lies." Molly pulled out a hair clip, a balloon pump, and a stolen birthday card. "You distract the clown; I swipe the toys." Bill sighed, wiping sweat from his forehead. "Last time you swiped my sandwich." "Last time you tried to steal a goldfish. This is professional." Molly checked her watch. "We have twenty minutes until the piñata breaks and everyone sees us hauling a trampoline." Bill nodded slowly. "If this fails, I blame the clown." "I already told him you're his cousin." "That was mean." "It was strategic." Molly crouched at the fence. "On three. One, two—" The birthday music blared from a cheap speaker. The door swung open. A child shouted, "Are you the clown?" Bill froze. "No, I'm the robber." Molly shrugged. "We can still steal the presents if we move fast."
created_at
"2026-09-01T13:57:14.018Z"
9/1/2026, 1:57:14 PM
model
"thinkingmachines/inkling-small-20260730"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
180
moderation_latency
(null)
generation_time
57550
tokens_prompt
75
tokens_completion
10901
native_tokens_prompt
74
native_tokens_completion
11989
native_tokens_completion_images
(null)
native_tokens_reasoning
10563
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
0.0144201
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788271034-IQWLVkS4aMWQOtBT0AeU"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788271034-oK541ByveQ8ZbiDJpTUG"
upstream_id
"chatcmpl-RD5I3dYbpbY8luNKLMhrwi8D"
provider_responses
0
endpoint_id
"d1d9657b-3c3a-49b5-8f81-33204e7c71c3"
id
"chatcmpl-RD5I3dYbpbY8luNKLMhrwi8D"
is_byok
false
latency
80
model_permaslug
"thinkingmachines/inkling-small-20260730"
provider_name
"DeepInfra"
status
200
total_cost
0.0144201
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
27.17%
Matches word count
n/a
neededClean
false
words
219
20.88%
Dialogue to Total Word Ratio
Ratio: 61.19%, Deviation: 11.19%
neededClean
false
wordsTotal
219
wordsDialogue
134
24.0233%