NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M36TGVKY5F8C044H4TDS7P24
Run Details
Model:
Xiaomi MIMO v2.6 Flash
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
32.8s
Cost:
$0.000224
Provider:
Xiaomi
Evaluation summary
Score
Evaluator
Details Link
14.30%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
7.1507%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 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
Molly spread the floor plan across the scarred kitchen table and jabbed a finger at the basement. The Martin-Whitfield birthday party would be in full swing by two o'clock, and thirty-seven eight-year-olds would be too distracted by a magician named Gary to notice two adults walking off with every present under the moon bounce. "So that's the entrance," she said, tapping the back door. "What if the back door's locked?" Bill asked, leaning forward with both elbows on the plan. "Then we use the window." "What if the window's locked?" Molly stared at him. "Bill, what if you stop asking what if and start asking how do we get paid." He held up his hands. "I'm just doing my job. Logistics." "Your job," she said slowly, "is that you're surprisingly small, you can fit through a dog flap, and you're not on any federal watch lists." "That's a gift, not a job." "It's a job." She clicked a pen. "Here's the plan. I go in the front at one-thirty. I'm a friend of the mother's." "We don't know the mother's name." "Janet. Her name is Janet. I know this." "Since when?" "Since I've been planning this for two weeks while you were at the gym." Bill sat back. "I was at your wedding, Molly. I know how you plan things. You planned that wedding with a color-coded spreadsheet." "Exactly. And it was beautiful." "Half the flowers died." "The flowers are not the point." She cleared her throat. "Janet and I enter the house together. I'll have a gift bag, plausible deniability. You come around the side, crawl through the dog flap, and position yourself near the wrapping pile. When Gary does the disappearing trick—" "Gary's doing a disappearing trick?" "His website says he makes things disappear. Probably the dad." "That's a crime in itself." "When the kids are gathered for the magic show, I'll create a distraction. Something about a fire alarm, maybe. You grab every bag, every box, every envelope, and you move them to the station wagon." "Whose station wagon?" "Yours." "Ol' Rusty out by the tracks?" "That's the one. I've already put blankets in the back so it doesn't squeal when you load it up." Bill nodded slowly. "This is actually well thought out." "Don't sound so surprised." "I'm not surprised. I'm concerned. What if a kid cries?" "Then a kid cries. We're not stealing from children, Bill. We're stealing from their parents. The kids didn't pay for those presents. Janet did. Janet has a Yale ring and a rental house and a salary that could cover our winter." "She has a rental house?" "She's a venture capitalist." Bill exhaled through his nose. "Fine. What's the split?" "Seventy-thirty." "I do the crawling." "You also have the car. And the criminal record that makes me look trustworthy by comparison. Seventy-thirty is generous." He pointed at her. "Sixty-forty or I fall asleep on the job." "Sixty-five, thirty-five, and you buy dinner." "Done." Molly rolled up the floor plan and tucked it under her arm. The party started at two. Gary the magician had no idea what was about to vanish.
created_at
"2026-09-23T09:46:02.756Z"
9/23/2026, 9:46:02 AM
model
"xiaomi/mimo-v2.6-flash-20260921"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3062
moderation_latency
(null)
generation_time
32745
tokens_prompt
75
tokens_completion
830
native_tokens_prompt
71
native_tokens_completion
766
native_tokens_completion_images
(null)
native_tokens_reasoning
48
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
0.00022442
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790156762-dylLnm8i5lx5td4TM1fN"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790156762-KtDiY0WEU7u5emPEO3OF"
upstream_id
"cd871aa5-ae17-4220-a1ed-01e45a145b28_cd984e7340f747238965f766697c4419"
provider_responses
0
endpoint_id
"6f7ea660-c5e2-492e-8a39-ec254953b3ae"
id
"cd871aa5-ae17-4220-a1ed-01e45a145b28_cd984e7340f747238965f766697c4419"
is_byok
false
latency
2756
model_permaslug
"xiaomi/mimo-v2.6-flash-20260921"
provider_name
"Xiaomi"
status
200
total_cost
0.00022442
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Xiaomi"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
14.30%
Matches word count
n/a
neededClean
false
words
521
0.00%
Dialogue to Total Word Ratio
Ratio: 74.25%, Deviation: 24.25%
neededClean
false
wordsTotal
532
wordsDialogue
395
7.1507%