NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M36SQZ6NDYEHC87EPKKTDDRT
Run Details
Model:
Xiaomi MIMO v2.6 Pro
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
33.4s
Cost:
$0.000684
Provider:
Xiaomi
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.9920%
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 spread the floor plans across the kitchen table while Bill hovered behind her, chewing on a pretzel stick like a conductor's baton. "So the little birthday brat's name is Timmy Wentworth," Molly said, tapping a crayon-drawn diagram. "Five years old. Party starts at two on Saturday." "Five years old. That's a milestone birthday in the present-receiving world." "It is. Hence why we're going." "How many kids are we talking about?" "Twelve. Twelve little vermin, each bringing a wrapped gift. Do the math." "Twelve gifts." Bill whistled. "What's the current market value on a five-year-old's birthday present?" "Whatever their parents spent at whatever overpriced toy store they shop at. Could be two grand total." "Two grand. For a kid who's still eating paste." "We don't need to understand it, Bill. We just need to exploit it." "Okay, walk me through it." "Two o'clock, the parents start dropping off kids. Three o'clock, cake and ice cream. Three fifteen, the sugar crash begins. Three thirty, presents. We go in at three thirty-five." "Why three thirty-five?" "Because they open presents at three thirty. Everyone's attention is on little Timmy tearing through wrapping paper like a tiny, deranged wolf. That gives us five minutes of chaos before anyone notices the gift mountain is shrinking." "What's our cover?" "You're a magician. A birthday magician." Bill choked on his pretzel. "I'm a what?" "A magician. You get hired to do a magic show. I called the Wentworths last week posing as a talent agent. Mrs. Wentworth was thrilled. She said it would be 'absolutely enchanting.'" "Mrs. Wentworth." "Mrs. Wentworth." "I don't know any magic tricks." "I bought you a kit. It's in the closet. Rabbit hat, silk scarves, a deck of cards that has all the same suit." "Isn't that just cheating?" "That's literally what magic is, Bill. I also need you to make one of the gifts disappear during your act." "What if the kids notice?" "Kids are terrible witnesses. They'll think it's part of the show. Meanwhile I'll be in the gift room pretending to be Mrs. Wentworth's estranged cousin from Cleveland." "And nobody questions this?" "Parents at children's parties are sleep-deprived sociopaths running on mimosa fumes. A strange woman near the presents is the least of their problems." "Okay, what about getting the presents out?" "Wheel them out through the garage in Timmy's own wagon. It's enormous. I've measured it." "You measured the wagon?" "I broke in Tuesday and measured the wagon." "Of course you did." "One last thing. Under no circumstances are you to put on the rabbit hat. It looks like a hamster died on your head." "It came with the kit!" "And it's staying in the bag. You wear the top hat. Black tie, white gloves, the whole thing. You look like a magician, you smell like success." Bill sighed and grabbed another pretzel. "Fine. But if a kid asks me to pull a quarter out of their ear, I'm doing it." "Fine. But you're keeping the quarter."
created_at
"2026-09-23T09:32:27.226Z"
9/23/2026, 9:32:27 AM
model
"xiaomi/mimo-v2.6-pro-20260921"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
8380
moderation_latency
(null)
generation_time
33126
tokens_prompt
75
tokens_completion
829
native_tokens_prompt
71
native_tokens_completion
751
native_tokens_completion_images
(null)
native_tokens_reasoning
55
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
0.000684255
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790155947-v6FwjwOSF6Cg1CfUa89q"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790155947-G9IcK7cKYYSzOAARDal6"
upstream_id
"e6e90afd-7b29-40f8-9493-f99fd7577d9f_9e03e3479f7c4ad5a3de52566dc25483"
provider_responses
0
endpoint_id
"2605413e-4a82-494f-ba65-d75f37ac3f11"
is_byok
false
latency
270
model_permaslug
"xiaomi/mimo-v2.6-pro-20260921"
provider_name
"DeepInfra"
status
429
1
endpoint_id
"4354fc36-b8ab-4ced-aa8c-0efb6b4523f1"
id
"e6e90afd-7b29-40f8-9493-f99fd7577d9f_9e03e3479f7c4ad5a3de52566dc25483"
is_byok
false
latency
5326
model_permaslug
"xiaomi/mimo-v2.6-pro-20260921"
provider_name
"Xiaomi"
status
200
total_cost
0.000684255
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
99.98%
Matches word count
n/a
neededClean
false
words
498
0.00%
Dialogue to Total Word Ratio
Ratio: 91.49%, Deviation: 21.49%
neededClean
false
wordsTotal
505
wordsDialogue
462
49.9920%