NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCVK8SNKZSHJP9W6Q1Z83V2
Run Details
Model:
Thinking Machines Inkling
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
8.6s
Cost:
$0.002823
Provider:
Together
Evaluation summary
Score
Evaluator
Details Link
6.09%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
3.0453%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 70% 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
"So, the plan is smash the piñata, but leave the candy, take the gifts, and vanish like the tooth fairy in a recession." "Bill, we're not smashing the piñata. The piñata is a decoy." "I thought the piñata was guard duty." "No, the guard duty is Mrs. Henderson with a Bluetooth headset and a vendetta." "She hates clowns." "Exactly. So I dress as a clown." "You dress as your worst nightmare?" "I wear a frown and steal the crown." "No crowns. We're here for presents, Bill." "I brought a sack. It says 'Laundry' on the side." "Perfect. Nobody suspects laundry at a birthday party." "Exactly. I blend in with the chaos of screaming children and balloons that smell like regret." "What's the entry point?" "The bouncy castle. I enter inflated." "You can't fit in a bouncy castle with a laundry sack of Legos." "It's conceptual entry." "So it's mental trespassing." "Yes, but with gloves." "Did you bring gloves?" "I brought oven mitts. They match my theme." "Your theme is what?" "Sad magician who forgot the trick is theft." "Bill, listen. The presents are under the table with the mermaid tablecloth." "Mermaids don't have tables. They have shells." "The point is camouflage." "Got it. I pretend I'm shell-shocked." "No. You pretend you're the uncle who brought balloons." "I am the uncle. The balloons are my alibi." "Then where are the balloons?" "In my head." "So you're entering with mental balloons and mental entry?" "Correct. But the sack is real. And very heavy with imaginary presents." "Bill, I need you focused. The gifts are wrapped in dinosaurs and unicorns." "So we steal dinosaurs and unicorns." "We steal whatever's wrapped. Even if it's socks." "Socks? At a party?" "Grandmas wrap socks. It's a trap." "So we steal socks too." "Yes. We are comprehensive thieves." "Do we need a code word?" "Code word is 'Sprinkles.'" "If I say sprinkles, do I run?" "No, you freeze like you're admiring the cake." "The cake is a distraction?" "The cake is a lie. Nobody eats it until after the presents." "So we strike during present-opening?" "No! We strike before present-opening. We take them unopened." "That's heartless." "Bill, heartless is not leaving a thank-you card." "Should I write one?" "From the ghosts of party past." "Will the parents chase us?" "Parents chase everything. That's why we wear black." "I'm wearing yellow. It's cheerful deception." "You'll glow like a warning light." "I'm the warning. I'm the yellow sign that says 'Caution: Stealing Joy.'" "Bill, are you sure about this?" "I'm sure about the sack. I'm unsure about the mermaid tablecloth." "If it sparkles, avoid it." "Sparkles are dangerous?" "Sparkles are evidence." "So I avoid sparkles, avoid the cake, avoid Mrs. Henderson, and steal socks." "And dinosaurs." "And unicorns." "And mental balloons." "Yes. But mostly the sack." "Then let's go be the worst guests they've ever invited."
created_at
"2026-07-25T14:41:47.838Z"
7/25/2026, 2:41:47 PM
model
"thinkingmachines/inkling-20260715"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
182
moderation_latency
(null)
generation_time
8386
tokens_prompt
75
tokens_completion
736
native_tokens_prompt
73
native_tokens_completion
679
native_tokens_completion_images
(null)
native_tokens_reasoning
0
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
0.00282295
router
(null)
provider_responses
0
endpoint_id
"9911deb9-f44e-4e18-87fe-9d7b60acee72"
id
"otYVvmd-6z2FuN-a20bed722a04348b"
is_byok
false
latency
166
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-1784990507-cBFIrl8RXBL4v4ws1zm6"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784990507-RuDd7LuU9nB3wEJFBtd2"
upstream_id
"otYVvmd-6z2FuN-a20bed722a04348b"
total_cost
0.00282295
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
6.09%
Matches word count
n/a
neededClean
false
words
477
0.00%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 30.00%
neededClean
false
wordsTotal
481
wordsDialogue
481
3.0453%