NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M36SP30K8R1M3WK04Z2A29VP
Run Details
Model:
Xiaomi MIMO v2.6 Pro
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
1m 30s
Cost:
$0.000633
Provider:
Xiaomi
Evaluation summary
Score
Evaluator
Details Link
93.65%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
46.8252%
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
The stolen blueprint was spread across the kitchen table like a treasure map drawn by a toddler with a crayon addiction. Molly adjusted her reading glasses and leaned over it. Bill was already eating chips off the blueprint, leaving grease stains over what appeared to be the living room. "Alright, Bill, pay attention. The party starts at two. Birthday boy's name is Dennis, turning six. Approximately twenty children in attendance, plus parents." She tapped a greasy chip spot on the blueprint. "The presents will be stacked right here, by the fireplace." "By the fireplace? That's convenient. Warm while we work." "We won't be warm. We'll be stealing from a six-year-old." "Right, right. Cold work. Got it." "Stop eating the blueprint." "You want a chip?" "I do not want a chip." Molly took a chip and ate it. "The guests arrive at two. The cake comes out at three. There's a magician scheduled for three-thirty, which is perfect cover because every child and parent in that room will be watching him pull a rabbit out of something." "What if he's a really good magician?" "Bill, magicians at six-year-olds' birthday parties are not really good magicians. This guy once called himself 'The Amazing Dave' and accidentally released two doves into a ventilation shaft." "Sounds like my kind of show." "The window we need to exploit is the pin-the-tail game at four o'clock. All the kids go to the backyard. Parents supervise. That's our window. We go in through the back kitchen door which Mrs. Partridge leaves unlocked because she always does because she's seventy-four and trusts humanity." "Should we feel bad about this?" "Is that a serious question?" "No, but I feel like I should ask." Molly held up a flashbang. "We won't need this." "Then why are you holding it?" "Habit." She put it away. "Now, the presents. I count fourteen gift bags and one suspiciously large wrapped box that I believe is the big-ticket item. Possibly a bicycle. Possibly a gaming console. Either way, that's our payday." "How much is a six-year-old's birthday haul actually worth?" "More than you'd think. Aunt Linda alone spent four hundred dollars last year on one kid's party. And there was a Target gift card taped to a stuffed bear worth fifty. The bear was worth eight." "You've really studied this." "I've been doing party recon for six months. I have a spreadsheet, Bill." "Of course you do." "The getaway car is parked two blocks down. I'll take the gift bags first. You grab the big box. Out the back, over the Hendersons' fence, and we're ghosts." "Over the Hendersons' fence? Their dog tried to eat me last time." "That dog weighs four pounds and is mostly decorative." "It had very strong opinions about my ankle." "Meet me here at one-fifirty. Wear something that looks like you're attending a children's party." "Can I wear the shirt with the dinosaurs on it?" "That's actually perfect." "Finally. Validation."
created_at
"2026-09-23T09:31:25.592Z"
9/23/2026, 9:31:25 AM
model
"xiaomi/mimo-v2.6-pro-20260921"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1866
moderation_latency
(null)
generation_time
89749
tokens_prompt
75
tokens_completion
793
native_tokens_prompt
71
native_tokens_completion
692
native_tokens_completion_images
(null)
native_tokens_reasoning
41
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
0.000632925
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790155885-qrChupSISXUuONOy0G6e"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790155885-0ONofwmgQMMFqEAPXHyy"
upstream_id
"446a616f-5d81-4e1f-aad8-a206004ca878_331f7097f25d4b379da1151a4f20ee79"
provider_responses
0
endpoint_id
"4354fc36-b8ab-4ced-aa8c-0efb6b4523f1"
id
"446a616f-5d81-4e1f-aad8-a206004ca878_331f7097f25d4b379da1151a4f20ee79"
is_byok
false
latency
1777
model_permaslug
"xiaomi/mimo-v2.6-pro-20260921"
provider_name
"Xiaomi"
status
200
total_cost
0.000632925
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
93.65%
Matches word count
n/a
neededClean
false
words
491
0.00%
Dialogue to Total Word Ratio
Ratio: 85.29%, Deviation: 15.29%
neededClean
false
wordsTotal
503
wordsDialogue
429
46.8252%