NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M36SM53X92D9J3K9SHVSFJP1
Run Details
Model:
Xiaomi MIMO v2.6 Flash
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
24.2s
Cost:
$0.000210
Provider:
Xiaomi
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
0.01%
Dialogue to Total Word Ratio
(details)
50.0064%
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
Bill spread the blueprints across the diner table and stabbed a greasy finger at the third floor of the suburban home. The paper was a rough photocopy he'd acquired from a very reluctant catering supplier named Gerald, who had since developed a lifelong fear of door-to-door salesmen. "So the party starts at three," Molly whispered, leaning forward as though the woman at the next table might be an informant. Bill nodded. "Thirty-seven kids, nine of them under five. Those are the unpredictable ones. Last time I worked a room full of toddlers, a little girl figured out my safecracking code in thirty seconds and then fell asleep on my shoes." "Let's aim for the seven-year-olds," Molly said, tapping a pencil against a photocopied layout of the house. "Better presents. More financial thinking. A seven-year-old in this neighbourhood is getting gift cards." "Nobody leaves gift cards under the tree," Bill muttered, scanning a handwritten list of what Gerald had called the "generous" households. He pointed at a circled address. The Hendersons. "These people always buy the good stuff. Last year at a fundraiser, they tipped a valet twenty bucks for parking a Civic." Molly's eyes went wide. "The Hendersons are in our zone? I thought that section belonged to Ricky's crew." "Ricky's crew got caught at a garden centre in May. It's ours now." Bill adjusted his fake mustache even though they were alone in the booth, a habit he had picked up from a movie he'd watched seven times. "We hit after the first round of pass-the-parcel. That's when the adults are distracted by the sugar crash." "What's your cover?" Molly asked, already unfolding her worst-fitting disguise bag. "I'm the new neighbour. I brought a casserole. Something passive." Bill paused. "Something brown." "Brown casserole. Bold choice." "I don't actually know how to make a casserole. I bought a frozen one and I'll transfer it into a proper dish at the last second. Basic misdirection." He pulled out a small notebook and began sketching escape routes. "Gifts are in the living room. We grab them and exit through the kitchen to the back garden, then over the fence into the Thompsons' yard. They're out of town." "According to who?" "Gerald." Molly raised an eyebrow. "Gerald from the catering company is also your real estate informant?" "Gerald has many talents and one grievance against civic order." Bill checked his watch. "We go in at three-twelve. I'll enter through the front door, you come through the side passage where the dog gate is broken." "The Hendersons don't own a dog." "Exactly. The gate is broken for no reason, which means it's been broken for years, which means nobody bothers fixing it. Beautiful, broken, forgotten. That's where you live." Molly tucked the blueprints into her jacket and stood up, sliding a twenty across the table for the coffee neither of them had finished. "If I hear the words 'guess what's under my shoe,' I'm aborting." Bill nodded solemnly. "God help whoever says it."
created_at
"2026-09-23T09:30:22.211Z"
9/23/2026, 9:30:22 AM
model
"xiaomi/mimo-v2.6-flash-20260921"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2561
moderation_latency
(null)
generation_time
24171
tokens_prompt
75
tokens_completion
809
native_tokens_prompt
71
native_tokens_completion
713
native_tokens_completion_images
(null)
native_tokens_reasoning
44
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
0.00020958
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790155822-QPnR4D8neKHURjFEwqyz"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790155822-BrB5H7QlxmlZGFu5b1CE"
upstream_id
"50d5f208-5f49-45c4-a81c-b89beb3586cc_24af10b8718e487eac2d1c3b780dca42"
provider_responses
0
endpoint_id
"6f7ea660-c5e2-492e-8a39-ec254953b3ae"
id
"50d5f208-5f49-45c4-a81c-b89beb3586cc_24af10b8718e487eac2d1c3b780dca42"
is_byok
false
latency
2479
model_permaslug
"xiaomi/mimo-v2.6-flash-20260921"
provider_name
"Xiaomi"
status
200
total_cost
0.00020958
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
100.00%
Matches word count
n/a
neededClean
false
words
499
0.01%
Dialogue to Total Word Ratio
Ratio: 63.33%, Deviation: 13.33%
neededClean
false
wordsTotal
510
wordsDialogue
323
50.0064%