NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ04Q1KHAKEMEVR9XK68EYEP
Run Details
Model:
Xiaomi MIMO v2.5 Pro
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
8.4s
Cost:
$0.001193
Provider:
Xiaomi
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
86.64%
Dialogue to Total Word Ratio
(details)
93.2794%
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
"So we're really doing this," Bill whispered, adjusting his ski mask. "A children's party." "It's not just any party," Molly said. "It's a five-year-old's birthday at the country club. These kids are getting iPads, drones, designer backpacks." "Designer backpacks? For kindergarteners?" "Trust-fund kindergarteners, Bill." "Right. So what's the plan?" "You're the clown." "I'm the what?" "The clown. There's a booking mix-up—real clown's got food poisoning. You show up, entertain the kids, keep them distracted." "What do I do? I don't know clown things." "Make balloon animals." "I can't make balloon animals." "How hard can it be?" "I tried once. It looked like a balloon murder scene." "Perfect. The kids will love you. Meanwhile, I slip into the gift room disguised as catering staff." "And how do you know where the gift room is?" "I sent the birthday boy's mom a very convincing email about party logistics." "You catfished a mom?" "I prefer 'social engineering.' Now honk your nose and let's go." "What if the real clown shows up?" "Then we improvise. We're professionals, Bill." "We absolutely are not." "Fake it till you make it. That's step one of every heist manual ever written." "Is there a step two?" "Don't get caught by kindergarteners."
created_at
"2026-04-24T16:21:08.353Z"
4/24/2026, 4:21:08 PM
model
"xiaomi/mimo-v2.5-pro-20260422"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1248
moderation_latency
(null)
generation_time
8231
tokens_prompt
77
tokens_completion
417
native_tokens_prompt
315
native_tokens_completion
361
native_tokens_completion_images
(null)
native_tokens_reasoning
55
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
0.0011932
router
(null)
provider_responses
0
endpoint_id
"5c24ecc9-5ba1-4af0-8877-3402889e7d0a"
id
"734a21d880ba48d8a5c2b33d50aa63a0"
is_byok
false
latency
1248
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-1777047668-3XxJSTC3sYhhbJVsCGNz"
session_id
(null)
api_type
"completions"
id
"gen-1777047668-BJKlVcxMJt48rR9P5E1e"
upstream_id
"734a21d880ba48d8a5c2b33d50aa63a0"
total_cost
0.0011932
cache_discount
0.0002048
upstream_inference_cost
0
provider_name
"Xiaomi"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.92%
Matches word count
n/a
neededClean
false
words
203
86.64%
Dialogue to Total Word Ratio
Ratio: 96.15%, Deviation: 6.15%
neededClean
false
wordsTotal
208
wordsDialogue
200
93.2794%