NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ060CR3R9KEB0V16KFT45N0
Run Details
Model:
Xiaomi MIMO v2.5
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
6.4s
Cost:
$0.000758
Provider:
Xiaomi
Evaluation summary
Score
Evaluator
Details Link
43.38%
Matches word count
(details)
93.02%
Dialogue to Total Word Ratio
(details)
68.1972%
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 what are we looking at, Bill?" "Twelve kids, ages five to seven. One clown. Thirty-two presents." "Thirty-two?" "Mrs. Henderson goes overboard every year." "Weapons?" "Gummyswords and water pistols." "What about the clown?" "Terrified of him. Big makeup. Big shoes." "We go during the cake," Molly said, tapping the blueprint spread across the table. "The cake?" "Every kid sits down. Clown does his thing. That's our window." "How long?" "Seven minutes, tops." "What about the dog?" "There's no dog, Bill. Read the intel." "That's the Hendersons' house. Every Henderson has a dog." "Fine. We bring sausage. Dog gets sausage. We get presents." "Beautiful. What's the exit strategy?" "Through the back door, into the van." "What if the van gets blocked?" "Then we carry the presents through Mrs. Patterson's yard like we're bringing donations to charity." "That's... actually genius." "I know." "What's our cut?" "Seventy-thirty. I planned everything." "Sixty-forty. I'm the muscle." "You weigh a hundred and forty pounds, Bill." "Dense muscle." "We'll discuss percentages in the van. Now get the sausage." "Regular or smoked?" "Do I look like a millionaire?" "Regular it is."
created_at
"2026-04-24T16:43:43.248Z"
4/24/2026, 4:43:43 PM
model
"xiaomi/mimo-v2.5-20260422"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
831
moderation_latency
(null)
generation_time
6228
tokens_prompt
77
tokens_completion
439
native_tokens_prompt
311
native_tokens_completion
358
native_tokens_completion_images
(null)
native_tokens_reasoning
70
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
0.00075848
router
(null)
provider_responses
0
endpoint_id
"2af4bf94-26fa-42b9-bce0-8b11071e105a"
id
"2c2ab3dfa5e742ea934b73a716870b56"
is_byok
false
latency
743
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-1777049023-BMWeAe0trb876Jim9RjH"
session_id
(null)
api_type
"completions"
id
"gen-1777049023-z45AZJMNwcNmefOpGKc2"
upstream_id
"2c2ab3dfa5e742ea934b73a716870b56"
total_cost
0.00075848
cache_discount
0.00008192
upstream_inference_cost
0
provider_name
"Xiaomi"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
43.38%
Matches word count
n/a
neededClean
false
words
183
93.02%
Dialogue to Total Word Ratio
Ratio: 95.19%, Deviation: 5.19%
neededClean
false
wordsTotal
187
wordsDialogue
178
68.1972%