NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-20-01M5C6B5HSXRBGMC1WF1GPWRQT
Run Details
Model:
DeepSeek V4.1 Flash 1017 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
28.1s
Cost:
$0.002484
Provider:
InferenceNet
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.9995%
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
Molly unfolded the birthday invitation on the van’s dashboard. “Right, Bill, the target is Little Timmy’s seventh birthday party, Saturday, two o’clock, seventeen children, one bouncy castle, and a gift table with an estimated retail value of four thousand pounds.” Bill squinted at the invitation. “Four thousand? For a seven-year-old? What’s on there, a gold toothbrush?” “Lego, mainly. Plus a drone, a scooter, and something called a ‘deluxe slime laboratory.’ We take the lot.” “And how do we get past the parents?” “Easy. You’re the entertainment.” “I’m the what?” “The magician. I booked you as ‘The Great Bilbo.’” “Molly, I can’t do magic. I can do one card trick and it’s mostly a distraction while I steal the card.” “Perfect. Do that. While the kids are watching the wrong hand, I’m at the present table with a laundry sack.” “And the bouncy castle?” “That’s our exit. We deflate it, roll it toward the fence, and use it as a soft landing for the gifts.” “That’s insane.” “That’s why it’s brilliant. Nobody suspects a magician and a party planner.” “I’m not wearing a cape.” “You’re wearing the cape. It has pockets.” Bill rubbed his temples. “What about the birthday boy? He’ll notice his presents leaving.” “That’s why we brought the decoy presents. Wrapped empty boxes. We swap them out.” “Empty boxes? That’s cruel.” “They’re children, Bill. They’ll be high on cake and adrenaline. They won’t open anything until Monday.” “And if they do?” “Then we’re already in Brighton.” “What about the clown?” “There is no clown. I checked.” “There’s always a clown.” “Not this time. The mother hired a face painter and a petting zoo.” “A petting zoo?” “Three rabbits and a very tired donkey.” “Donkey’s a problem.” “Donkey’s a distraction. You pull a scarf from its ear, kids scream, I take the scooter.” “I’m not pulling anything from a donkey’s ear.” “Fine. The rabbit.” “Molly.” “Bill, focus. Timeline. We arrive at one-forty as the magician and his assistant.” “I thought I was the magician.” “You are. I’m the assistant. I assist by stealing things.” “What if someone asks for a trick?” “You do the card thing. Then you make a coin disappear.” “I can’t make a coin disappear.” “You can. You put it in your pocket and look surprised.” “That’s not magic.” “It’s showmanship.” “What if the parents recognize us?” “From where? The Whitmore wedding? We were catering staff.” “You were catering staff. I was trapped in a suit of armor.” “And you were very convincing.” Bill sighed. “Fine. What’s my cut?” “Sixty-forty.” “Sixty for me?” “Sixty for me. I did the planning.” “I’m doing the donkey.” “Rabbit.” “I want fifty-fifty.” “Done. But you’re buying the laundry sack.” Molly folded the invitation. “And Bill, if you see a child crying, do not offer them a decoy box.” “Why not?” “Because last time you told a crying child it was ‘a lesson in disappointment,’ and we almost got arrested by a vicar.” Bill nodded. “And no crying children.” “Agreed.” “Deal.” Molly grinned.
created_at
"2026-10-20T08:20:15.04Z"
10/20/2026, 8:20:15 AM
model
"deepseek/deepseek-v4.1-flash-20261017"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
143
moderation_latency
(null)
generation_time
28028
tokens_prompt
75
tokens_completion
4555
native_tokens_prompt
67
native_tokens_completion
4958
native_tokens_completion_images
(null)
native_tokens_reasoning
4156
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
0.00248436
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1792484415-loB9OtGWsO2tmJIMvHKg"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1792484415-FpZtdq8AXh5s2Mo0NUTN"
upstream_id
"gv2_wk1CUEfqI1VgO1359uLCg"
provider_responses
0
endpoint_id
"4231aea9-73af-4a2f-bd14-660b1d8b13b2"
id
"gv2_wk1CUEfqI1VgO1359uLCg"
is_byok
false
latency
143
model_permaslug
"deepseek/deepseek-v4.1-flash-20261017"
provider_name
"InferenceNet"
status
200
total_cost
0.00248436
cache_discount
(null)
upstream_inference_cost
0
provider_name
"InferenceNet"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
501
0.00%
Dialogue to Total Word Ratio
Ratio: 94.46%, Deviation: 24.46%
neededClean
false
wordsTotal
505
wordsDialogue
477
49.9995%