NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0B25G3EXKHR1Z73CQGJ2AM
Run Details
Model:
Xiaomi MIMO v2.5
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
8.1s
Cost:
$0.001604
Provider:
Xiaomi
Evaluation summary
Score
Evaluator
Details Link
75.16%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
37.5778%
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 spread the blueprints across the table, though they were clearly just a crayon drawing ripped from a refrigerator. Bill squinted at the purple squiggles. "What am I looking at?" "It's the floor plan, Bill. The kid drew it himself and posted it online. His mom thought it was cute." "Security?" "One golden retriever named Sir Biscuit and a Roomba that gets stuck under the couch." Bill nodded slowly. "High risk." "We're going in Saturday at two PM. Peak cake time. Every adult will be distracted by that singing goat mascot the parents hired." "You're joking." "Does the Joker joke, Bill?" "Constantly. That's his whole thing." Molly ignored him. "I go in disguised as the face painter. You go in as the balloon guy. We converge on the present table during musical chairs." "Musical chairs? That's our window?" "Thirty seconds of pure chaos, Bill. Kids screaming, parents filming, nobody watching the corner where fourteen gift bags are sitting unattended. It's beautiful." "What's in the bags that makes this worth it?" Molly leaned forward. "The Hendersons are rich, Bill. Last year their kid got a solid gold piggy bank, a genuine diamond-encrusted tiara for a three-year-old, and stock certificates." "Stock certificates? At a fourth birthday?" "Tech money, Bill. They don't follow normal rules." Bill rubbed his chin. "What about the clown?" "What clown?" "The listing says entertainment includes Bubbles the Clown." Molly froze. "That wasn't in the intelligence." "I saw it on the event page. Bubbles does magic tricks and balloon animals. He'll be everywhere. Clowns have no loyalty." "Fine. We neutralize Bubbles." "How?" "You do the balloon animals. Challenge him to a duel. While he's distracted, I hit the table." "A balloon animal duel?" "You're telling me you can't out-twist some party clown?" Bill straightened up. "I once made a full-scale poodle in under ten seconds at my nephew's birthday." "That's the spirit." "What about the dog?" "Sir Biscuit is a golden retriever. You bring jerky. Every golden retriever on earth will follow jerky to the ends of the earth." Molly pulled a small duffel bag from under the table and unzipped it. Inside were two Hawaiian shirts, a pack of face paint, a bag of beef jerky, and a water gun filled with ketchup. "What's the ketchup for?" "Distraction. If anything goes wrong, I spray myself and yell about a nosebleed. Nobody questions a nosebleed. They just feel bad." "Brilliant." They stared at each other across the table, two professionals on the edge of their greatest caper. "When this is over," Bill said quietly, "we never speak of it." "Agreed. Now go practice your balloon sword. We need you sharp." Bill stood, pocketed the jerky, and headed for the door. He paused. "Molly?" "Yeah?" "We're stealing from children." "We're stealing from their parents. The children won't even notice. They'll be too busy crying about musical chairs." Bill considered this, nodded once, and disappeared into the night.
created_at
"2026-04-24T18:12:04.238Z"
4/24/2026, 6:12:04 PM
model
"xiaomi/mimo-v2.5-20260422"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
586
moderation_latency
(null)
generation_time
7922
tokens_prompt
77
tokens_completion
924
native_tokens_prompt
311
native_tokens_completion
781
native_tokens_completion_images
(null)
native_tokens_reasoning
87
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
0.00160448
router
(null)
provider_responses
0
endpoint_id
"2af4bf94-26fa-42b9-bce0-8b11071e105a"
id
"bd6fb24203724bb4b70cae51da6bf084"
is_byok
false
latency
548
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-1777054324-7a3NNbHuAjJTtlIJMGhr"
session_id
(null)
api_type
"completions"
id
"gen-1777054324-vmteP8R3QPyXCSG7XZd1"
upstream_id
"bd6fb24203724bb4b70cae51da6bf084"
total_cost
0.00160448
cache_discount
0.00008192
upstream_inference_cost
0
provider_name
"Xiaomi"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
75.16%
Matches word count
n/a
neededClean
false
words
487
0.00%
Dialogue to Total Word Ratio
Ratio: 75.56%, Deviation: 25.56%
neededClean
false
wordsTotal
491
wordsDialogue
371
37.5778%