NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCTWCZ7XR7H86XJMNVDQBWT
Run Details
Model:
Thinking Machines Inkling (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
10m 28s
Cost:
$0.033186
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
43.38%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
71.6892%
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 flattened the stolen crayon map against the ice cream truck’s frost-covered dashboard. Bill circled a suburban backyard with a glitter pen that had seen better birthdays. The target was a fifth birthday party featuring a bouncy castle, one terrified magician, and presents wrapped in paper loud enough to wake sleeping grandparents. Bill pulled on rubber gloves shaped like dinosaur paws and adjusted his ski mask printed with smiling puppies. "The castle holds dozens of gifts wrapped in noise." Molly sipped coffee that tasted like broken promises. "We steal from toddlers?" Bill loaded bacon-scented boots into his sequined messenger bag beside a crowbar, explaining that parents would be hypnotized by scarves pulled from armpits. She pointed to a purple smudge labeled Sprinkles; eleven pounds of trembling fury patrolled near juice boxes. The escape route required navigating past face-painting tables, a mechanical pony smelling of regret, and adults too deep in prosecco to notice strangers hauling duffel bags of plastic bricks. Bill stuffed confetti grenades into his pockets. "My mother wanted accounting." The truck jingle played mournfully as they parked behind a dinosaur hedge. Molly checked her watch. Precisely at two, chaos would bloom. They slipped out, bags empty and hopeful, stepping onto the lawn ready to breach the balloon arch. "This is accounting with chaos," Molly said.
created_at
"2026-07-25T14:29:18.448Z"
7/25/2026, 2:29:18 PM
model
"thinkingmachines/inkling-20260715"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
980
moderation_latency
(null)
generation_time
627692
tokens_prompt
75
tokens_completion
7506
native_tokens_prompt
75
native_tokens_completion
8182
native_tokens_completion_images
(null)
native_tokens_reasoning
7149
native_tokens_cached
32
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
0.03318554
router
(null)
provider_responses
0
endpoint_id
"d6b9d68e-115a-49d7-81cd-1ad1c6942b0e"
id
"chatcmpl-RWnhNUkxXQ2R8nrAqnxOMPLr"
is_byok
false
latency
62
model_permaslug
"thinkingmachines/inkling-20260715"
provider_name
"DeepInfra"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer
(null)
request_id
"req-1784989758-WSsfV9dKszSCung3Lc6x"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784989758-aXMLEcQ3fZQQtO2CmfSb"
upstream_id
"chatcmpl-RWnhNUkxXQ2R8nrAqnxOMPLr"
total_cost
0.03318554
cache_discount
0.00002656
upstream_inference_cost
0
provider_name
"DeepInfra"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
43.38%
Matches word count
n/a
neededClean
false
words
217
100.00%
Dialogue to Total Word Ratio
Ratio: 10.00%, Deviation: 0.00%
neededClean
false
wordsTotal
220
wordsDialogue
22
71.6892%