NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ05XRRB6QXEMA6FQ9Y8NJ8Y
Run Details
Model:
Xiaomi MIMO v2.5
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
7.8s
Cost:
$0.001201
Provider:
Xiaomi
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
95.52%
Dialogue to Total Word Ratio
(details)
47.7579%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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
"You sure about this, Molly? A six-year-old's party? Seems low-stakes." Bill adjusts his tiny black ski mask, which keeps riding up. "It's genius, Bill. Genius! Operation Sugar Rush is a go. The parents will be loaded with wine and weak from chaperoning musical chairs. The loot is untouched, stacked neatly by the door. Our approach?" "Molly, they have a bounce house." "A tactical distraction. When the hired clown, 'Giggles,' finishes his set at 3:15, he'll deflate it. Chaos. Crying. We slip in through the patio during the emotional aftermath." "The loot, Molly. What's the score?" "Forty Play-Doh cans and a My Little Pony. In and out. We fence the Pony on EBay. The rest is just for the thrill." Bill blinks. "The thrill? Molly, this is a glorified playdate. And what about the dog? The flyer says 'Winston the Welcoming Pup.'" "Winston is the key. He responds only to the word 'snack.' We bring cheese. He'll be our inside man. Now, the exit?" "We exit through the doggy door. With the Pony." "No. We exit calmly with the presents, pretending to be the parents of a child named 'Finn.' Finn doesn't exist. He's our ghost. We load the loot into the van labeled 'Non-Descript Plumbing.' It's the perfect cover." "Right. Snack, ghost, plumbing. Got it. This is why you're the brains." "And you're the brawn. Now stop eating the planning cheese. That's for Winston." "Sorry. Nervous appetite."
created_at
"2026-04-24T16:42:17.24Z"
4/24/2026, 4:42:17 PM
model
"xiaomi/mimo-v2.5-20260422"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
605
moderation_latency
(null)
generation_time
7674
tokens_prompt
77
tokens_completion
625
native_tokens_prompt
311
native_tokens_completion
569
native_tokens_completion_images
(null)
native_tokens_reasoning
211
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
0.00120096
router
(null)
provider_responses
0
endpoint_id
"2af4bf94-26fa-42b9-bce0-8b11071e105a"
id
"59a6c53e9f414ada9d49f81e888c63b1"
is_byok
false
latency
549
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-1777048937-srdsChdA7yKmy5pvIHze"
session_id
(null)
api_type
"completions"
id
"gen-1777048937-z76ErA6CQifY1kld1b2L"
upstream_id
"59a6c53e9f414ada9d49f81e888c63b1"
total_cost
0.00120096
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
237
95.52%
Dialogue to Total Word Ratio
Ratio: 94.63%, Deviation: 4.63%
neededClean
false
wordsTotal
242
wordsDialogue
229
47.7579%