NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCYF31RJNCEB0BYTKM7HJC9
Run Details
Model:
Thinking Machines Inkling (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
38.4s
Cost:
$0.014817
Provider:
Together
Evaluation summary
Score
Evaluator
Details Link
75.16%
Matches word count
(details)
85.02%
Dialogue to Total Word Ratio
(details)
80.0877%
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 checked her watch. "Party starts at three." "Perfect," Bill said. "We go in at three-oh-one." "You want to crash a five-year-old's birthday?" "I want to liberate twenty square feet of unopened goods." "That’s not a heist, that’s parenting in reverse." "Call it what you want. There’s a PlayStation in that pile." "How do you know?" "I followed the aunt on Instagram. Tagged the box." "You stalked a relative for intel?" "I prefer market research." "We're monsters." "We're entrepreneurs. Balloons are distraction. You pop them, I grab bags." "Pop balloons? I’m not a clown." "You’re chaos. I’m wearing the fake mustache." "That mustache is a crime scene." "So is leaving gifts under a piñata. Evening the score." "Bill, they're children." "Children with better toys than me. Moral line or weak grip?" "My grip is excellent. I can carry thirty presents." "Then let’s do this. Door unlocked, cake on table, parents distracted by an unlicensed magician." "That magician is our inside man?" "No, he's bad at cards. He's cover. North presents, south presents. No crying, no witnesses, no cake for Bill." "That’s my rule." "Your rule is mine. Van in four minutes." "Four minutes? There's a bouncy castle." "Exactly. Bounce out with goods." Molly grinned. "You're insane." "And you're in. Three-oh-one. Don't be late."
created_at
"2026-07-25T15:31:56.609Z"
7/25/2026, 3:31:56 PM
model
"thinkingmachines/inkling-20260715"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
164
moderation_latency
(null)
generation_time
37960
tokens_prompt
75
tokens_completion
3076
native_tokens_prompt
75
native_tokens_completion
3640
native_tokens_completion_images
(null)
native_tokens_reasoning
3314
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
0.014817
router
(null)
provider_responses
0
endpoint_id
"9911deb9-f44e-4e18-87fe-9d7b60acee72"
id
"otYmMJk-6z2FuN-a20c36e7aadcff48"
is_byok
false
latency
150
model_permaslug
"thinkingmachines/inkling-20260715"
provider_name
"Together"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer
(null)
request_id
"req-1784993516-T1QcnfDN2yAmUv37jg8A"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784993516-LbRVwB1rtqSD1jH2YnzC"
upstream_id
"otYmMJk-6z2FuN-a20c36e7aadcff48"
total_cost
0.014817
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Together"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
75.16%
Matches word count
n/a
neededClean
false
words
213
85.02%
Dialogue to Total Word Ratio
Ratio: 96.35%, Deviation: 6.35%
neededClean
false
wordsTotal
219
wordsDialogue
211
80.0877%