NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ08JK7QY24KFFGRNZVM7HKZ
Run Details
Model:
Xiaomi MIMO v2.5 Pro
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
10.0s
Cost:
$0.001349
Provider:
Xiaomi
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0004%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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
Molly smoothed the crinkled blueprint on the table, a drawing of a bouncy castle with suspiciously precise measurements. “It’s perfect, Bill. The Little Critters’ Animal Adventure Party. Security will be lax.” Bill peered over her shoulder, adjusting his glasses. “Lax? There’ll be a dozen shrieking kids high on cake. It’s a logistical nightmare, not to mention ethically dubious.” “Ethics are flexible,” Molly said, her eyes gleaming. “I’m going as the hired princess. You can be the clown. We’ll corner the gift table during the magic show.” Bill sighed, rubbing his temples. “A clown. I have a PhD in art history.” “And that’s why you’ll handle the dexterity challenges. We’ll exchange the real presents for decoy boxes filled with… educational puzzles.” “They’ll notice!” “That’s why I’ve also hired three raccoons,” Molly declared, unfurling a separate, more chaotic blueprint. “They’ll cause a diversion near the snack table. Utter pandemonium.” Bill stared. “You cannot rent raccoons.” “Not with that attitude.” Molly grinned, tapping the blueprint. “Operation Pinata is a go.”
created_at
"2026-04-24T17:28:36.864Z"
4/24/2026, 5:28:36 PM
model
"xiaomi/mimo-v2.5-pro-20260422"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1295
moderation_latency
(null)
generation_time
9857
tokens_prompt
77
tokens_completion
510
native_tokens_prompt
315
native_tokens_completion
413
native_tokens_completion_images
(null)
native_tokens_reasoning
159
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
0.0013492
router
(null)
provider_responses
0
endpoint_id
"5c24ecc9-5ba1-4af0-8877-3402889e7d0a"
id
"df65ee92b10a4471b49762f8175c1a7f"
is_byok
false
latency
1217
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-1777051716-IGFa4EWJ8R7ZCdaJ7CYI"
session_id
(null)
api_type
"completions"
id
"gen-1777051716-jXnUpEnWou9wpkk2dhHo"
upstream_id
"df65ee92b10a4471b49762f8175c1a7f"
total_cost
0.0013492
cache_discount
0.0002048
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
167
0.00%
Dialogue to Total Word Ratio
Ratio: 69.46%, Deviation: 19.46%
neededClean
false
wordsTotal
167
wordsDialogue
116
0.0004%