NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ08EB70AZE3PE4R7V8VZ8H7
Run Details
Model:
Xiaomi MIMO v2.5
Test:
Dialogue tags
Scenario:
Write 500 words with 30% dialogue
Duration:
11.7s
Cost:
$0.001746
Provider:
Xiaomi
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0000%
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
Molly adjusted her oversized rainbow wig, the scratchy synthetic fibers tickling her forehead. “Okay, listen up, Bill. Operation Birthday Blitz is a go.” She peered through the binoculars at the brightly colored house across the street, balloons bobbing on the porch like silent sentinels. “The intel is solid. The target is a double-birthday bash for twin six-year-olds, Leo and Lily. The haul is potentially enormous.” Bill, currently squeezed into a polka-dot clown suit two sizes too small, shifted uncomfortably on the curb. “It feels wrong, Molly. Their little faces. Their trusting, sticky little hands. What kind of monsters steal from toddlers?” “The kind of monsters who want to retire to a non-extradition country with a private collection of limited-edition Robo-Rexes,” Molly replied crisply. She handed him a walkie-talkie shaped like a slice of watermelon. “You’re on clown duty. Your mission is to create a diversion in the backyard. The big distraction—the one where you ‘accidentally’ spray the parents with the silly string and cause a minor, hilarious panic.” “And what’s your play?” “I’m the hired help,” Molly said, smoothing down her khaki shorts. “Mrs. Henderson hired ‘Party Professionals, Inc.’ to assist. I have a clipboard and a fake mustache. I can get anywhere.” She pointed a decisive finger. “Your window is when the kids are inside for cake. They’ll be focused on the candles, the singing, the sugar high. That’s when I slip into the living room where all the presents are piled high.” Bill tugged at his polyester collar. “A whole pile? That seems greedy. Maybe just one? The big one with the shiny robot on the box?” “No, Bill. We take the lot. We leave a decoy—a beautifully wrapped box full of old phone books. It’s the perfect crime. They’ll shake it, hear the thud, and assume it’s something heavy and wonderful like a encyclopedia set. It’s diabolically boring.” “Do you think the silly string is really the best diversion?” Bill asked, looking deeply skeptical. “What if someone has an allergy?” “Then they’ll have a slightly more exciting afternoon. Focus!” Molly snapped her fingers. “The key is timing. You create the chaos. I create the opportunity. We meet at the extraction point—the treehouse in the back. Are you clear on the exit strategy?” “Don’t trip over the slip-and-slide on the way to the treehouse. Got it.” “And Bill?” Molly lowered her binoculars, a rare glint of humor in her eyes. “Try to look like you’re having fun. You’re supposed to be a clown. Right now, you look like a sad man in a prison of primary colors.” Bill attempted a smile. It looked more like a wince. “How’s that?” “Terrifying. Perfect. Now, go make some noise. Operation Birthday Blitz begins… now.”
created_at
"2026-04-24T17:26:17.581Z"
4/24/2026, 5:26:17 PM
model
"xiaomi/mimo-v2.5-20260422"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
725
moderation_latency
(null)
generation_time
10752
tokens_prompt
77
tokens_completion
1039
native_tokens_prompt
311
native_tokens_completion
852
native_tokens_completion_images
(null)
native_tokens_reasoning
226
native_tokens_cached
256
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
0.00174648
router
(null)
provider_responses
0
endpoint_id
"2af4bf94-26fa-42b9-bce0-8b11071e105a"
id
"4597b60bebe14fda8f2b908293b84b0e"
is_byok
false
latency
629
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-1777051577-IwE4FHJdPPLYZfvAKACQ"
session_id
(null)
api_type
"completions"
id
"gen-1777051577-ECoa2xxg7cTn2c2iXK5X"
upstream_id
"4597b60bebe14fda8f2b908293b84b0e"
total_cost
0.00174648
cache_discount
0.00008192
upstream_inference_cost
0
provider_name
"Xiaomi"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
456
0.00%
Dialogue to Total Word Ratio
Ratio: 75.11%, Deviation: 45.11%
neededClean
false
wordsTotal
466
wordsDialogue
350
0.0000%