NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ09J67B8PPJFCQB0KT5PCXQ
Run Details
Model:
Xiaomi MIMO v2.5
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
5.3s
Cost:
$0.000794
Provider:
Xiaomi
Evaluation summary
Score
Evaluator
Details Link
86.38%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
61.5841%
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
"All right, Bill, here's the plan. We hit the Hendersons' house Saturday at two p.m." "Two p.m.? That's broad daylight, Molly." "Exactly. The party's at two. Thirty kids hopped up on sugar and cake. Nobody's watching the door." "So what's my role?" "You're the clown." "I'm not wearing a red nose, Molly." "It's a disguise, Bill. You blend in. You make balloon animals. You distract the children while I load up the presents." "There's also a bouncy castle involved. How do I explain the bouncy castle to my back?" "You don't. You ignore the bouncy castle. The bouncy castle is not our target." "What is our target?" "Seven wrapped boxes under a small plastic tree, Bill. There's a train set in there. Do you know what a vintage Lionel train set goes for online?" "I don't know what a Lionel train set is." "Neither will the children once we leave. Now, what happens if someone suspects us?" "You do the voice." "What voice?" "The baby voice, Molly. You know the one." "Fine. I do the voice. But only in emergencies." "And if the dog barks?" "Dogs love clowns, Bill." "Dogs hate clowns, Molly." "Then we bring treats." "Dog treats?" "No. We steal them from the snack table. See? It all connects."
created_at
"2026-04-24T17:45:52.12Z"
4/24/2026, 5:45:52 PM
model
"xiaomi/mimo-v2.5-20260422"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
633
moderation_latency
(null)
generation_time
5126
tokens_prompt
77
tokens_completion
422
native_tokens_prompt
311
native_tokens_completion
376
native_tokens_completion_images
(null)
native_tokens_reasoning
76
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
0.00079448
router
(null)
provider_responses
0
endpoint_id
"2af4bf94-26fa-42b9-bce0-8b11071e105a"
id
"54cf24dcd11a4af6b7a86f81ac617a4a"
is_byok
false
latency
587
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-1777052752-kSb9DCJbkxTPYjawQBKz"
session_id
(null)
api_type
"completions"
id
"gen-1777052752-YptjWwqdbcZcJy3bEugC"
upstream_id
"54cf24dcd11a4af6b7a86f81ac617a4a"
total_cost
0.00079448
cache_discount
0.00008192
upstream_inference_cost
0
provider_name
"Xiaomi"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
86.38%
Matches word count
n/a
neededClean
false
words
211
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
211
wordsDialogue
211
61.5841%