NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ012RWESMJJ3J9QSQ98075G
Run Details
Model:
Xiaomi MIMO v2.5
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
9.3s
Cost:
$0.001419
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 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
The suburban house vibrated with the force of thirty screaming children and a hired entertainer whose voice had reached frequencies previously unknown to science. From behind a perfectly manicured hedge, Molly and Bill watched through binoculars. “My god,” Bill whispered. “It’s a fortress. The target is the pile. Ten o’clock, corner of the living room. Looks like at least two dozen wrapped parcels.” “I see it,” Molly said, lowering her own binoculars. “It’s the motherlode. Unattended. A weak underbelly of pure, unadulterated loot.” “The weak underbelly is covered in sticky hands and flying cake crumbs. How do we get in?” Molly tapped her temple. “Professionalism, Bill. We integrate. We pose as entertainers.” “They already have a guy in a dragon suit. He looks dead inside.” “Exactly. We’re an upgrade. We’re the ‘Magic & Mayhem’ duo. We’ll need a rabbit—“ she glanced around, “—and a saw. A big one. For the trick.” “A saw? At a party for a five-year-old named ‘Cayden’?” “It’s called showmanship. While they’re distracted by my perilous sawing in half, you, as my assistant, will create a diversion.” “What kind of diversion?” “You’ll trip. spectacularly. Over the presents. They’ll scatter. You’ll be horribly embarrassed.” “And then?” “And then we bag the scattered loot and flee in the ensuing confusion. Simple. Elegant.” Bill stared at the pulsating windows of the house. “Molly, I feel I must point out the plan has two major flaws. First, we don’t have a rabbit. Second, my mother banned me from wearing fake mustaches after the ‘incident’.” “Details,” Molly dismissed, pulling a floppy top hat from her bag. “Improvisation is the heart of the craft. Now, you need to look helpless and accident-prone. Practice falling.” Bill sighed and executed a truly pathetic, unconvincing stumble. “Like this?” “Perfect,” Molly beamed. “You’re a natural. We’re going to steal so many presents.”
created_at
"2026-04-24T15:17:38.332Z"
4/24/2026, 3:17:38 PM
model
"xiaomi/mimo-v2.5-20260422"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
762
moderation_latency
(null)
generation_time
9186
tokens_prompt
77
tokens_completion
809
native_tokens_prompt
311
native_tokens_completion
678
native_tokens_completion_images
(null)
native_tokens_reasoning
222
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
0.00141896
router
(null)
provider_responses
0
endpoint_id
"2af4bf94-26fa-42b9-bce0-8b11071e105a"
id
"3c8472e104b84ce0a1a8a2f83656d7ad"
is_byok
false
latency
705
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-1777043858-uMXI9GXCXuK4vESN1HCc"
session_id
(null)
api_type
"completions"
id
"gen-1777043858-1yVkdrGs4Dk7c6LpcBnc"
upstream_id
"3c8472e104b84ce0a1a8a2f83656d7ad"
total_cost
0.00141896
cache_discount
0.00006144
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
306
0.00%
Dialogue to Total Word Ratio
Ratio: 72.49%, Deviation: 22.49%
neededClean
false
wordsTotal
309
wordsDialogue
224
0.0000%