NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ043P2DW9RYW0Y3SQQKPCHX
Run Details
Model:
Xiaomi MIMO v2.5
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
12.0s
Cost:
$0.001716
Provider:
Xiaomi
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0000%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 70% 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 tapped the blueprint on the table. “The operation is at 1600 hours. Target: the Henderson residence. Objective: acquire all birthday presents.” Bill leaned in, squinting. “That’s the one with the bouncy castle, right? I call dibs on the bouncy castle after we’re done.” “You’re not here for the bouncy castle, Bill. Focus. Security?” “Mrs. Henderson bought a new security system. It’s called a ‘baby monitor.’ Top of the line. It picks up every coo and gurgle.” Molly groaned. “So we’re dealing with audio surveillance. Any perimeter guards?” “Their cat, Mr. Whiskers. He’s on the patio. Mean little fella. Tried to claw my shoelace last recon.” “Non-lethal. noted. We go in through the back, past the cat. Diversion?” “I brought the perfect thing.” Bill held up a noisy, crinkly, oversized lollipop. “Kid kryptonite. One wave of this and they’ll follow me anywhere, forming a trail right out the back gate.” “That’s… actually not terrible. But what about the adults? They’ll be serving juice and making small talk. They’ll see you.” “I’ll be ‘Uncle Bill,’ the fun relative who just arrived. I’ll do magic tricks. Terrible ones. They’ll be so busy being politely confused, they won’t notice you looting the gift table.” “And if someone asks where you came from?” “I’ll say I drove in from ‘the city.’ That always works. Vague and impressive.” Molly nodded, making a note. “The presents themselves. How do we transport them?” “Two giant pillowcases. I’ve got them. Very professional.” “Pillowcases? We’re not amateurs, Bill. What about the noise? Rustling wrapping paper is like a siren to parents.” “We wait until the cake. When they sing ‘Happy Birthday,’ the noise level will be maximum. We move on the crescendo of ‘cha-cha-cha.’” Molly slowly looked up from her notes. “You’ve really thought about this.” “It’s my cousin’s kid’s party. I have an inside man. He wants the blue truck with the flashing lights. He’ll be our lookout.” “Excellent. Timeline?” “15:45: Infiltration. 16:00: Diversion deployed. 16:15: Cake singing commences. 16:16: The Big Grab. 16:17: Egress via hedge maze. 16:18: We’re gone, laughing all the way to the toy store.” Molly cracked a small smile. “Alright. It might just work. But remember the first rule of party heists.” “Never take the last cookie?” “No. Never underestimate a five-year-old with a new toy. They become instantly, irrationally territorial.” “Right. So, we leave the blue truck?” Molly paused. “...No. We absolutely take the blue truck.” “Thought so. For my nephew, you understand.” “Purely professional necessity.”
created_at
"2026-04-24T16:10:33.942Z"
4/24/2026, 4:10:33 PM
model
"xiaomi/mimo-v2.5-20260422"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1908
moderation_latency
(null)
generation_time
11881
tokens_prompt
77
tokens_completion
972
native_tokens_prompt
311
native_tokens_completion
837
native_tokens_completion_images
(null)
native_tokens_reasoning
173
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
0.00171648
router
(null)
provider_responses
0
endpoint_id
"2af4bf94-26fa-42b9-bce0-8b11071e105a"
id
"4990480a20864507b4fbb1be37b0e05b"
is_byok
false
latency
1878
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-1777047033-P7yt6aMSuBpBdbTMSM1W"
session_id
(null)
api_type
"completions"
id
"gen-1777047033-YVuWFWZWTd63FFTrWRSC"
upstream_id
"4990480a20864507b4fbb1be37b0e05b"
total_cost
0.00171648
cache_discount
0.00008192
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
414
0.00%
Dialogue to Total Word Ratio
Ratio: 90.38%, Deviation: 20.38%
neededClean
false
wordsTotal
416
wordsDialogue
376
0.0000%