NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ02AP0M4T41P9ZCH9W72HGC
Run Details
Model:
Xiaomi MIMO v2.5
Test:
Dialogue tags
Scenario:
Write 500 words with 30% dialogue
Duration:
13.5s
Cost:
$0.002051
Provider:
Xiaomi
Evaluation summary
Score
Evaluator
Details Link
35.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
17.5011%
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 unrolled the crumpled blueprint across the park bench, her finger tracing a path around a series of crayon-drawn rooms. “Okay, listen up, Bill. The target is 42 Maple Drive. Birthday party for one ‘Timmy,’ age six. Theme: Dinosaurs.” Bill squinted, adjusting his fake mustache. “Dinosaurs. Got it. So, we’re after… what, exactly? Tiny plastic triceratops? A pet rock?” Molly sighed. “The big one, Bill. The Mega-Rex 5000. Remote-controlled, breathes LED fire, costs more than our rent. It’s in the north corner of the living room, next to the bouncy castle exit.” She tapped a smudge on the paper. “The intel says the package is wrapped in shiny blue paper with a giant yellow bow.” “Right. Infiltration strategy?” Bill asked, pulling a notebook titled ‘Heists for Idiots’ from his jacket. “Phase one: I go in as ‘Auntie Mo,’ the long-lost cousin. I bring a fruit salad.” Molly held up a Tupperware container. “Phase two: You enter through the back gate when the clown does his ‘silly magic’ routine. Distraction is key.” “Clowns are chaotic,” Bill nodded, scribbling. “I like it. What’s my disguise?” “You’re the ‘Bubbleologist.’ You have a gig from two to three. You bring the giant wands, the soapy solution, the works.” “Perfect. I’ll create a diversionary foamfront.” Bill grinned. “So, during the bubble chaos, I slip into the living room, secure the Mega-Rex, and exfiltrate via the laundry room window?” “Negative,” Molly said sharply. “The laundry room is a known choke point. Mrs. Henderson’s prize-winning chili is simmering in there. The smell alone would blow our cover. We use the pet door in the kitchen. I’ve widened it with a butter knife.” “A butter knife? That’s your tool for the job?” “It’s a versatile instrument, Bill. I also used it to pry open the intel dossier.” She pointed again. “Once you have the Rex, you head straight for the slide in the backyard. It’s a direct chute to the alley.” Bill pondered this. “Won’t a kid be on the slide?” “Exactly. You say ‘special delivery for the party,’ give them a high-five, and slide down with the prize. No one suspects the bubble man.” “You’ve really thought this through,” Bill said, impressed. “Of course. Now, the exit strategy. I’ll cause a mild incident with the piñata—knock it into the punch bowl. While everyone’s distracted by the sticky, colorful flood, you and I melt away to the waiting van.” “And our share?” Bill asked. “I get the Mega-Rex to sell to a tech hobbyist in the next city. You get to keep all the leftover goodie bags. I hear they have juice boxes shaped like dinosaurs.” Bill’s eyes lit up. “The little ones with the straws? Sold. Let’s do this.” He stood up, cracking his knuckles. “For Timmy’s Mega-Rex and my juice boxes.” Molly rolled up the blueprint, a smirk on her face. “Let’s go steal a childhood. Gently.”
created_at
"2026-04-24T15:39:26.11Z"
4/24/2026, 3:39:26 PM
model
"xiaomi/mimo-v2.5-20260422"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
607
moderation_latency
(null)
generation_time
13431
tokens_prompt
77
tokens_completion
1135
native_tokens_prompt
311
native_tokens_completion
994
native_tokens_completion_images
(null)
native_tokens_reasoning
278
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
0.00205096
router
(null)
provider_responses
0
endpoint_id
"2af4bf94-26fa-42b9-bce0-8b11071e105a"
id
"addca370c125407cadc4801dca727d1b"
is_byok
false
latency
554
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-1777045166-55q6d4vEUsSoHfCFyHT4"
session_id
(null)
api_type
"completions"
id
"gen-1777045166-CXv8YhkbU7RZf59mclQC"
upstream_id
"addca370c125407cadc4801dca727d1b"
total_cost
0.00205096
cache_discount
0.00006144
upstream_inference_cost
0
provider_name
"Xiaomi"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
35.00%
Matches word count
n/a
neededClean
false
words
482
0.00%
Dialogue to Total Word Ratio
Ratio: 82.28%, Deviation: 52.28%
neededClean
false
wordsTotal
491
wordsDialogue
404
17.5011%