NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-01-01M1EMZC4JGF7TXNXDGAXTE6QW
Run Details
Model:
Thinking Machines Inkling Small (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
30.1s
Cost:
$0.003419
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
50.0000%
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
"Bill," Molly said, "the birthday party starts at two." "Perfect," Bill said, tightening his glittery present sack. "We hit the bounce house." "The bounce house is for children, Bill," Molly said. "You have a mustache and a serious plan." "I am emotionally available for bounce houses," Bill said. "The presents are stacked by the clown tunnel like a glittery fort." "The clown tunnel is a plastic tube with a sad rainbow that says 'Magic Entrance.'" "Still. Peak efficiency. Are we infiltrating this birthday or not?" "We are infiltrating because you bribed me with a pizza bagel," Molly said. "Correct. The mom is a retired police officer." "Then we bring cupcakes as a Trojan horse." "Those cupcakes have eyes," Molly said. "Mine have frosting," Bill said. "We'll blend in. If anyone asks, you are my cousin." "Your cousin?" "The van cousin. We enter at one-fifty." "You are wearing cat-ear headphones." "It is my look. How do we get past security?" "There are no guards," Bill said. "Only a balloon arch and a dad with a beard who thinks he is funny." "That dad is terrifying." "He might ask about the unicycle." "You don't own a unicycle." "I can steal one from the petting zoo." "That is worse than stealing presents." "We steal joy," Bill said. "Silver robot or plush unicorn?" "I want to leave before anyone screams." "We wear the present bags." "I am already wearing one. It says 'Happy Birthday Liam' in sparkles." "Perfect camouflage," Molly said. "Can we agree this is a terrible idea?" "I agree," Bill said. "Let's proceed."
created_at
"2026-09-01T14:11:38.777Z"
9/1/2026, 2:11:38 PM
model
"thinkingmachines/inkling-small-20260730"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
219
moderation_latency
(null)
generation_time
19867
tokens_prompt
75
tokens_completion
3112
native_tokens_prompt
74
native_tokens_completion
2821
native_tokens_completion_images
(null)
native_tokens_reasoning
2707
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
0.0034185
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788271898-feRvqwye30TaouTWnptP"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788271898-rvNZToiVI8vfDJ0iwyHy"
upstream_id
"chatcmpl-RiTjaygEECtlky2lHvSDmXJp"
provider_responses
0
endpoint_id
"0ed263b7-f746-4eb6-a14c-54f2e1cc2269"
is_byok
false
latency
10075
model_permaslug
"thinkingmachines/inkling-small-20260730"
provider_name
"Together"
status
504
1
endpoint_id
"d1d9657b-3c3a-49b5-8f81-33204e7c71c3"
id
"chatcmpl-RiTjaygEECtlky2lHvSDmXJp"
is_byok
false
latency
95
model_permaslug
"thinkingmachines/inkling-small-20260730"
provider_name
"DeepInfra"
status
200
total_cost
0.0034185
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
0.00%
Matches word count
n/a
neededClean
false
words
261
100.00%
Dialogue to Total Word Ratio
Ratio: 89.73%, Deviation: 0.27%
neededClean
false
wordsTotal
263
wordsDialogue
236
50.0000%