NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-01-01M1ENH193YMBR0G8CG4Z4MFDF
Run Details
Model:
Thinking Machines Inkling Small (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
2m 11s
Cost:
$0.014529
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
3.15%
Dialogue to Total Word Ratio
(details)
51.5670%
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 beret, which slipped over her eyes because she forgot her hair up. "Bill, is a children's party a soft target with juice boxes?" Bill scratched his beard, grown for this caper. "Soft target? Twelve toddlers, Mr. Giggles, and an astronaut piƱata. What's the security?" "One dad with a phone and a mom auditioning for reality," Molly said, pulling out a blueprint. "We enter through the inflatable slide. Its integrity is questionable, but so is our retirement plan." Bill frowned. "The slide exits into a ball pit of plastic eggs. Landmines for adults over five feet." "Good thing I brought knee pads," Molly said. "We split loot by color. Red for you, blue for me." "We need a distraction," Bill said, producing a rubber chicken. "I'll deploy it at the snack table." "That's a cry for help," Molly said. "Exactly," Bill said. "In comedy heists, the plan sounds clever until it fails. Ready?" Molly checked her watch, a toy clock from a previous job. "Midnight. But the party ends at four, so we're early." "Then let's be late," Bill said. They crept toward the bounce house, leaving crumbs that could only be breadcrumbs of destiny.
created_at
"2026-09-01T14:21:17.482Z"
9/1/2026, 2:21:17 PM
model
"thinkingmachines/inkling-small-20260730"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
619
moderation_latency
(null)
generation_time
130544
tokens_prompt
75
tokens_completion
9815
native_tokens_prompt
74
native_tokens_completion
12080
native_tokens_completion_images
(null)
native_tokens_reasoning
9517
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
0.0145293
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788272477-8Ko2xAUhobuOj5e6169C"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788272477-L6HRMnAEJyJri7Yorqn9"
upstream_id
"chatcmpl-RUSHyidh5FaMXayap1IO4LkP"
provider_responses
0
endpoint_id
"d1d9657b-3c3a-49b5-8f81-33204e7c71c3"
id
"chatcmpl-RUSHyidh5FaMXayap1IO4LkP"
is_byok
false
latency
477
model_permaslug
"thinkingmachines/inkling-small-20260730"
provider_name
"DeepInfra"
status
200
total_cost
0.0145293
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
99.98%
Matches word count
n/a
neededClean
false
words
198
3.15%
Dialogue to Total Word Ratio
Ratio: 63.64%, Deviation: 13.64%
neededClean
false
wordsTotal
198
wordsDialogue
126
51.5670%