NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ07DTAE1G8ZY0FC6C084XHN
Run Details
Model:
Xiaomi MIMO v2.5 Pro
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
15.7s
Cost:
$0.002045
Provider:
Xiaomi
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0008%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 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 peered through binoculars at the backyard chaos. Balloons, streamers, and shrieking children. "The 'Operation: Present Avalanche' target is in sight," she murmured. "A bouncy castle to the northwest, a cake table to the east." Bill, peering over her shoulder, nodded sagely. "And the loot. Look at the pile. Wrapped boxes of untold joy." "We go in at the peak of the pinata scramble," Molly said. "You create a diversion. Spill the juice box reservoir." "Brilliant. Chaos is our friend," Bill agreed. "Then you slip in, unmarked gifts only, into the oversized clown bag." "Right. And what's your primary task?" Molly asked. "Create a second diversion," Bill said, cracking his knuckles. "I'm going to operate the bouncy castle. Maximum turbulence." "That's... not the plan, Bill." "Plans are fluid, Molls. Once I launch three toddlers into a gentle, controlled orbit, no one's watching the gift table." Molly sighed, pinching the bridge of her nose. "Just... don't pop it. And for heaven's sake, if you hear 'Happy Birthday,' we abort. That's the signal for parental regrouping." "Copy that," he said. "Happy Birthday means defcon one. We ghost." "Exactly. Now, synchronize watches." "Right," Bill said, squinting at his wrist. "How do we synchronize if mine's always five minutes fast?" "We set everything to your watch. So we're five minutes early." "Proactive. I like it." The party horn echoed. "That's the third horn blast. Go time," Molly whispered. "You got it," Bill said, cracking his neck. "I'll cause a sensation." "Just cause a distraction, Bill. A. Distraction." "Semantics," he said, already jogging towards the castle. "Let's grab and go!" Molly watched him bounce towards the inflatable fortress, already sidestepping a toddler on a sugar high. "He's going to launch a child, isn't he?" She sighed, adjusted her clown-bag, and headed for the wrapping-paper battlefield.
created_at
"2026-04-24T17:08:31.705Z"
4/24/2026, 5:08:31 PM
model
"xiaomi/mimo-v2.5-pro-20260422"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1298
moderation_latency
(null)
generation_time
15615
tokens_prompt
77
tokens_completion
734
native_tokens_prompt
315
native_tokens_completion
645
native_tokens_completion_images
(null)
native_tokens_reasoning
180
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
0.0020452
router
(null)
provider_responses
0
endpoint_id
"5c24ecc9-5ba1-4af0-8877-3402889e7d0a"
id
"7e304638587d4de0a91690d01c878c90"
is_byok
false
latency
1217
model_permaslug
"xiaomi/mimo-v2.5-pro-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-1777050511-u30OiQI4bxJlK76hZHdB"
session_id
(null)
api_type
"completions"
id
"gen-1777050511-o5NUbm5jjCqmYpaslFko"
upstream_id
"7e304638587d4de0a91690d01c878c90"
total_cost
0.0020452
cache_discount
0.0002048
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
300
0.00%
Dialogue to Total Word Ratio
Ratio: 68.21%, Deviation: 18.21%
neededClean
false
wordsTotal
302
wordsDialogue
206
0.0008%