NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-01-01M1EM6072H8YE1NF537B5ED00
Run Details
Model:
Thinking Machines Inkling Small (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
30.8s
Cost:
$0.007537
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
0.49%
Matches word count
(details)
99.99%
Dialogue to Total Word Ratio
(details)
50.2432%
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
Bill tugged his ski mask over his eyes and frowned at the glittering yard signs, noting the bounce castle and a silver tray of juice boxes. "Molly, stealing from children violates human decency," he said. Molly slid behind a lawn gnome, consulting a crumpled map covered in cupcake crumbs and glitter. "Bill, it's humanitarian service," she said. "They have too many toys." "We're targeting a birthday bash with a clown named Festus?" Bill asked, adjusting his shoulder bag that read "Party Supplies" in purple marker. "Festus owes me. We enter through the garage, disable juice-box surveillance—" Molly said. "By drinking the juice?" "Exactly. We intercept presents during the cake cutting." Bill glanced through the window at small voices singing off-key near a piñata shaped like a birthday cake. "What if they notice us?" "We say we're inspectors for the Ministry of Sugar," Molly replied. "Hand me the sack. The piñata is in forty-five minutes." "If a child stares at us with innocent eyes, you talk," Bill said. "Deal. If they ask about the bag, it's a magic trick." "We're bad at magic." "Good at regret." Bill muttered, staring at the balloon arch that seemed to guard the door like a festive moat. "I should have been a dentist." Molly smirked, adjusting her sunglasses that seemed too cool for a children's party heist. "Too late. The presents await."
created_at
"2026-09-01T13:57:47.37Z"
9/1/2026, 1:57:47 PM
model
"thinkingmachines/inkling-small-20260730"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
780
moderation_latency
(null)
generation_time
30777
tokens_prompt
75
tokens_completion
5740
native_tokens_prompt
74
native_tokens_completion
6253
native_tokens_completion_images
(null)
native_tokens_reasoning
5388
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
0.0075369
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788271067-IGkmmyjqmkh64FcWF9RA"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788271067-Ee6SVBXdYn7BwGA6rQgD"
upstream_id
"chatcmpl-RnuFvzinw8698VCSGxy5YIIm"
provider_responses
0
endpoint_id
"d1d9657b-3c3a-49b5-8f81-33204e7c71c3"
id
"chatcmpl-RnuFvzinw8698VCSGxy5YIIm"
is_byok
false
latency
334
model_permaslug
"thinkingmachines/inkling-small-20260730"
provider_name
"DeepInfra"
status
200
total_cost
0.0075369
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
0.49%
Matches word count
n/a
neededClean
false
words
227
99.99%
Dialogue to Total Word Ratio
Ratio: 50.87%, Deviation: 0.87%
neededClean
false
wordsTotal
230
wordsDialogue
117
50.2432%