NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M36SWFHT0DXT69M42N8HTBHP
Run Details
Model:
Xiaomi MIMO v2.6 Pro
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
31.7s
Cost:
$0.000694
Provider:
Xiaomi
Evaluation summary
Score
Evaluator
Details Link
60.28%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
30.1376%
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 unfolded the party invitation across the hood of their van, smoothing out the creases with the side of her fist. She'd stolen it from a mailbox on Elm Street, and it was covered in glitter from where some child had decorated the envelope with what appeared to be a snowman made of glue and crushed peppermints. The van smelled like hot dogs and ambition. "Okay," Molly said, tapping the card with a pen. "Timmy Braddock. Turning seven. Saturday, two to four PM." "Two to four," Bill repeated, leaning against the open driver's side door. He was eating a banana in a way that made Molly want to throw it at him. "That's a narrow window. Ninety minutes to loot a house full of screaming seven-year-olds." "It's not the house we're looting, Bill. It's the gift pile." "There's a gift pile?" "There's always a gift pile. Kids this age get buried in presents. Parents spend more on a seven-year-old's birthday than they do on Christmas. It's a known sociological phenomenon." Bill chewed thoughtfully. "You made that up." "I read about it in a magazine." "You don't read magazines." "I read one magazine. It was in the dentist's office. The point is, there will be a table by the cake with all the gifts on it. Wrapped, easy to grab, high value." "What kind of value?" "Action figures. Building sets. One kid always gets a bicycle. I'm telling you, Bill, this is our retirement." Bill squinted at the invitation. "It says 'Pajama Party.' We need pajamas?" "We need pajamas." "We're dressing up? For a children's birthday party?" "Mingling is essential, Bill. We arrive as guests. We eat the pizza. We play the games. Then, during the magic show—" "Magic show?" "There's always a magic show." "That's not a sociological phenomenon. That's just how kids' parties work." "Exactly. During the magic show, when everyone's watching the guy pull scarves out of his hat, we make our move on the gift table." Bill peeled another banana from a bunch he'd produced from his jacket. Where was he keeping all these bananas? "I don't like it. Too many witnesses. Kids talk." "Kids talk about everything. No one's going to believe a seven-year-old detective." "The parents will notice." "The parents will be drunk on sangria. It's standard at these things. I saw it in a magazine." "You went back to that dentist." "I switched dentists, Bill. The point is the whole system works. We blend in, we wait for our moment, and we walk out with three hundred dollars worth of toys." Bill looked at the invitation again. "It says 'no gifts, please, just bring yourself and a smile.'" Molly stared at him. "There's no gift pile," Bill said. "There's always a gift pile, Bill. Parents lie about that. Nobody shows up to a kid's birthday empty-handed. Not in this economy of guilt." Bill sighed deeply, the way he always did right before he agreed to something stupid. "What size pajamas?" "Whatever's on sale at the discount store on Ninth. And Bill? Get the flannel ones. Flannel reads as trustworthy."
created_at
"2026-09-23T09:34:55.04Z"
9/23/2026, 9:34:55 AM
model
"xiaomi/mimo-v2.6-pro-20260921"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1565
moderation_latency
(null)
generation_time
31641
tokens_prompt
75
tokens_completion
831
native_tokens_prompt
71
native_tokens_completion
762
native_tokens_completion_images
(null)
native_tokens_reasoning
63
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
0.000693825
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790156095-ymLFlM9LVq2v3PYLwars"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790156095-earCYHKyd0uj6w5SSRPy"
upstream_id
"bd49d10a-b492-44e7-b33f-b1c14fd52249_3b00303a74574544ae502712fdc865f8"
provider_responses
0
endpoint_id
"4354fc36-b8ab-4ced-aa8c-0efb6b4523f1"
id
"bd49d10a-b492-44e7-b33f-b1c14fd52249_3b00303a74574544ae502712fdc865f8"
is_byok
false
latency
1484
model_permaslug
"xiaomi/mimo-v2.6-pro-20260921"
provider_name
"Xiaomi"
status
200
total_cost
0.000693825
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
60.28%
Matches word count
n/a
neededClean
false
words
515
0.00%
Dialogue to Total Word Ratio
Ratio: 70.69%, Deviation: 20.69%
neededClean
false
wordsTotal
522
wordsDialogue
369
30.1376%