NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ04226ABDC041JSV92R942J
Run Details
Model:
Xiaomi MIMO v2.5 Pro
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
11.2s
Cost:
$0.001466
Provider:
Xiaomi
Evaluation summary
Score
Evaluator
Details Link
35.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
67.5011%
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
The backyard was alive with the shrieks of children. In the bushes, Molly adjusted her binoculars. “Confirmed. The cake is a three-tier monstrosity. Presents are in a wicker basket by the back door.” “Brilliant,” Bill whispered. “We hit during ‘Pin the Tail on the Donkey’. Maximum distraction.” “Your job is the basket. Don’t trip over the bouncy castle.” “Have I ever tripped?” “Baltimore. The marble floor. The entire collection of rare coins went—” “—gloriously everywhere, yes. But I was wearing inappropriate footwear. Tonight: tactical sneakers.” “Fine. My job?” “You create a diversion.” “Why am I always the diversion?” “Because you have a louder voice. And the clown wig.” “I hate the clown wig. It smells like fear and popcorn.” “Put it on. When you see me grab the basket, you yell ‘Fire in the hole!’” “That’s not a child-friendly phrase, Bill.” “Yell ‘The dragon escaped!’ then. More thematic.” “What dragon?” “The one on the bouncy castle. Just look determined and run. We rendezvous behind the azaleas.” “With the loot?” “With enough presents to build our own dream house. Mostly Lego, I suspect.”
created_at
"2026-04-24T16:09:40.833Z"
4/24/2026, 4:09:40 PM
model
"xiaomi/mimo-v2.5-pro-20260422"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1637
moderation_latency
(null)
generation_time
11149
tokens_prompt
77
tokens_completion
546
native_tokens_prompt
315
native_tokens_completion
435
native_tokens_completion_images
(null)
native_tokens_reasoning
162
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
0.0014664
router
(null)
provider_responses
0
endpoint_id
"5c24ecc9-5ba1-4af0-8877-3402889e7d0a"
id
"424d98c796744de18baa754339d60403"
is_byok
false
latency
1553
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-1777046980-JaItApCmNMr0ZrHUetVG"
session_id
(null)
api_type
"completions"
id
"gen-1777046980-LgcxPELLnq2VnU8YR2EX"
upstream_id
"424d98c796744de18baa754339d60403"
total_cost
0.0014664
cache_discount
0.0001536
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
182
100.00%
Dialogue to Total Word Ratio
Ratio: 90.22%, Deviation: 0.22%
neededClean
false
wordsTotal
184
wordsDialogue
166
67.5011%