NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ00Z9WQWCWQJP3RKPEZD710
Run Details
Model:
Xiaomi MIMO v2.5
Test:
Dialogue tags
Scenario:
Write 500 words with 30% dialogue
Duration:
14.8s
Cost:
$0.002043
Provider:
Xiaomi
Evaluation summary
Score
Evaluator
Details Link
93.65%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
46.8248%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 30% 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 public park bench overlooking the playground was their war room. Molly, a wiry woman with a perpetually skeptical expression, unrolled the "blueprint"—a crayon-scrawled birthday invitation from a trash bin. "Alright, Bill, listen up," she whispered, jabbing a finger at the paper. "Saturday. 3 PM. The target: the Harrison kid's fifth birthday party. Intel suggests high-value assets. We're talking Legos, a remote-control dinosaur, probably a plush unicorn of some sort." Bill, a large, gentle-faced man currently trying to balance a pretzel on his nose, stopped. "Presents? From a kids' party? Isn't that... a little mean?" Molly sighed, the long-suffering sigh of a professional. "Mean? It's a victimless crime! The target doesn't even know what he's getting. He'll be just as happy with the wrapping paper. Our job is to relieve society of the burden of conspicuous consumption. Now, phase one: infiltration." "How? We gonna crash the bounce house?" Bill asked, the pretzel finally toppling. "Subtlety, William!" Molly snapped. "We're not bouncing. I go in as a parent. 'Oh, I'm Sarah's mom, she's already inside, such a rascal.' I gain entry to the present pile. You, you're the cake delivery boy." "Ooh, I like cake." "You're not eating it, you're using it. You create a distraction. A minor, frosting-based incident. While the adults are mopping up, I execute the swap." "Swap?" Molly pulled two identical, large gift bags from her backpack, both covered in cheerful dinosaur prints. "Phase two. I replace the entire pile with these bags containing... newspaper. By the time anyone notices, we're long gone with the good stuff." "Genius!" Bill beamed. "What if someone's watching the pile?" Molly grinned, a slightly feral expression. "That brings us to phase three: the clown." Bill paled. "Not Gerald." "Gerald owes me for that pigeon incident. He's our inside man. He starts his routine, maybe a little too enthusiastically. All eyes on him. The chaos is our camouflage." "So I just... dump cake?" "You do your 'oops' face. You've practiced it. The one that makes you look like a confused Saint Bernard. Then you melt into the background. Simple." Bill practiced the face. It was deeply unsettling. "And if it goes wrong?" "Plan B. You tie your shoelaces together and fall down the slide. I grab the bag and run. They'll be too busy laughing at you to notice." For a moment, Bill looked thoughtful. "You know, for a kids' party, this is a lot of work." "It's not work, Bill. It's artistry. The heist of the century." Molly stood, rolling up the crayon blueprint. "We hit them hard, we hit them fast, and we leave them with nothing but memories and sticky fingers. Any questions?" Bill raised his hand. "Can I wear the dinosaur hat from the craft table? For morale?" Molly pinched the bridge of her nose. "Only if it's absolutely necessary." "Everything's necessary for morale," Bill stated solemnly. "It's in the handbook." "We don't have a handbook!" "Well, maybe we should get one. Chapter one: Hat policy." He stood, stretching. "Okay. Let's go steal some joy. Professionally."
created_at
"2026-04-24T15:15:44.675Z"
4/24/2026, 3:15:44 PM
model
"xiaomi/mimo-v2.5-20260422"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
599
moderation_latency
(null)
generation_time
14703
tokens_prompt
77
tokens_completion
1121
native_tokens_prompt
311
native_tokens_completion
990
native_tokens_completion_images
(null)
native_tokens_reasoning
246
native_tokens_cached
192
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"
usage
0.00204296
router
(null)
provider_responses
0
endpoint_id
"2af4bf94-26fa-42b9-bce0-8b11071e105a"
id
"1da15de716a6448c9dbc603a3e83a0df"
is_byok
false
latency
555
model_permaslug
"xiaomi/mimo-v2.5-20260422"
provider_name
"Xiaomi"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777043744-oszq9St30gLwB1e0Dakw"
session_id
(null)
api_type
"completions"
id
"gen-1777043744-Qw20Kh8jDbVNa2p444Z4"
upstream_id
"1da15de716a6448c9dbc603a3e83a0df"
total_cost
0.00204296
cache_discount
0.00006144
upstream_inference_cost
0
provider_name
"Xiaomi"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
93.65%
Matches word count
n/a
neededClean
false
words
509
0.00%
Dialogue to Total Word Ratio
Ratio: 73.59%, Deviation: 43.59%
neededClean
false
wordsTotal
515
wordsDialogue
379
46.8248%