NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-01-01M1EN8AJ3PTSN954A53Q0D9N0
Run Details
Model:
Thinking Machines Inkling Small (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
1m 39s
Cost:
$0.015354
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
81.27%
Matches word count
(details)
64.35%
Dialogue to Total Word Ratio
(details)
72.8126%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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, are you sure?" Bill asked. "Bill, have you met kids?" Molly said. "Best toys." "These are toddlers with juice boxes, not vaults." "Juice boxes are liquid assets, and the presents are full of glitter." "Glitter is a deadly weapon, and you know my serious allergy." "We'll wear professional clown hazmat suits that make us look like medical staff." "What about parents?" "The 'forgot my glasses' look. We blend as awkward adults who brought store-bought cupcakes." "Store-bought? I thought we were sophisticated professionals." "We don't need sophistication when there's a piƱata. We go at 2:15, during the balloon routine." "Which clown?" "The broken-nose one." "Noted. Backyard fence?" "No, front door. Some dad named Kevin thinks community means leaving your door open for bears." "I hate Kevin and his open-door philosophy." "Good. You'll stay in the kitchen to distract adults with cryptocurrency and literal cheese fraud." "I'm good at cheese fraud." "Exactly. I'll grab the big presents with too much ribbon." "Caught?" "We're the entertainment. I'm a mime, and you're a very confusing magician." "I'll practice my mysterious vibe and my intimidating stare." "Bring the duffel." "Pink, says Princess. Adds character." "It holds four hundred cubic inches of stolen Legos. Let's go, Bill. The kid turns five, and he doesn't know what's coming."
created_at
"2026-09-01T14:16:32.075Z"
9/1/2026, 2:16:32 PM
model
"thinkingmachines/inkling-small-20260730"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
342
moderation_latency
(null)
generation_time
98503
tokens_prompt
75
tokens_completion
11526
native_tokens_prompt
74
native_tokens_completion
12767
native_tokens_completion_images
(null)
native_tokens_reasoning
11169
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
0.0153537
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788272192-q2EojSVGJkm8X8EnJIac"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788272192-l2H98qHocJwdyG5IIJZ6"
upstream_id
"chatcmpl-Rzl6C7mwWfo59wj08N0DVIAj"
provider_responses
0
endpoint_id
"d1d9657b-3c3a-49b5-8f81-33204e7c71c3"
id
"chatcmpl-Rzl6C7mwWfo59wj08N0DVIAj"
is_byok
false
latency
81
model_permaslug
"thinkingmachines/inkling-small-20260730"
provider_name
"DeepInfra"
status
200
total_cost
0.0153537
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
81.27%
Matches word count
n/a
neededClean
false
words
212
64.35%
Dialogue to Total Word Ratio
Ratio: 98.15%, Deviation: 8.15%
neededClean
false
wordsTotal
216
wordsDialogue
212
72.8126%