NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M36TM4DG3ZCWCF8VT8TSKJS2
Run Details
Model:
Xiaomi MIMO v2.6 Flash
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
1m 22s
Cost:
$0.000245
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
68.33%
Dialogue to Total Word Ratio
(details)
34.1643%
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
Bill pressed his ear against the doorframe. "You hear that?" Molly checked her watch. "Cake smashing. It's almost time for presents." She looked back at Bill. "What's the plan?" "Standard operation. Distract, enter, bag the loot, exit." "And the distraction?" Bill grinned. "Clown costume." Molly stared at him. "You own a clown costume?" "I own seven clown costumes." "Seven?" "I went through a phase." Bill rummaged through his duffel bag. "Here. You wear this one." Molly held up a ruffled collar and red nose. "I'm not wearing that." "You're wearing it. The birthday girl won't hesitate. She's two. She'll open her arms for anything." "So we're relying on a toddler's natural affection?" "The toddler is the key, Molly. Everyone knows you never turn away a toddler's hug." Molly examined the costume. "And what exactly do you do while I'm being embraced by a two-year-old?" "I slip in through the side door. The mother left it unlocked. I checked three times." "You checked three times." "Twice for the door. Once for the locks. It's all clear." Molly tucked the clown nose into her pocket. "And how many presents are we talking?" "I counted nineteen wrapped boxes. Heavy ones near the bookshelf. That's where the good stuff is." "How do you know it's the good stuff?" "The father is a lawyer. Lawyers buy expensive toys." "Lawyers' kids break expensive toys." "That's the beauty of it. The breakage justifies our theft. We're essentially recycling." Molly snorted. "Recycling. That's what you're calling this." "Look, do you want to stand here arguing with me or do you want presents?" "How many are for us?" "All nineteen." "Bill, we're not children." "Technically, every gift is technically for someone. We're just changing who." Molly paused. "The clown costume only buys you two minutes." "Three minutes. I'm good." "You timed yourself climbing through a side door?" "I timed myself climbing through a side door in the third clown costume. This one fits better." Molly shook her head and slipped the collar around her neck. "If this goes wrong, I'm blaming you." "You're already blaming me. You blame me before things go wrong. That way the blame is timely." "That's not how blame works." "It's how my blame works." Bill adjusted his duffel bag. "One more thing." "What?" "Sing happy birthday." "I'm not singing." "The parents expect it. If the clown doesn't sing, they'll get suspicious." "They'll get suspicious about everything else too." "Only the singing, Molly. Only the singing." Molly pulled the red nose over her face and inhaled through her nostrils. "Fine. But I'm choosing the song." "No requests. You'll sing it wrong and blow the whole operation." "Since when are you a birthday song purist?" "Since we're stealing birthday presents, Molly. Some things are sacred." Bill checked his watch. "Forty-five seconds." Molly grabbed the gift bags. "You're the worst co-conspirator I've ever had." "I'm the only co-conspirator you've ever had." "Still the worst." She shoved open the door. "Okay, Mr. Wonderful. Go steal from children." Bill slipped through the side door like smoke. Molly marched into the living room and heard the clown suit rustle as the toddler turned to see her. She knelt down, smiled beneath the red nose, and opened her arms. Behind the couch, she heard the rustling of paper and the soft zip of a duffel bag.
created_at
"2026-09-23T09:47:50.07Z"
9/23/2026, 9:47:50 AM
model
"xiaomi/mimo-v2.6-flash-20260921"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
419
moderation_latency
(null)
generation_time
81648
tokens_prompt
75
tokens_completion
924
native_tokens_prompt
71
native_tokens_completion
838
native_tokens_completion_images
(null)
native_tokens_reasoning
46
native_tokens_cached
0
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"
service_tier
(null)
usage
0.00024458
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790156870-Y9D5197HJvgnSgZv6tsQ"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790156870-wl0q5VoKMdJzW3e9uFfT"
upstream_id
"chatcmpl-RNPsZUts5gcgEI5aJuvqeaH0"
provider_responses
0
endpoint_id
"8f1a1d4b-adc8-465f-860a-4dc2aad88765"
id
"chatcmpl-RNPsZUts5gcgEI5aJuvqeaH0"
is_byok
false
latency
73
model_permaslug
"xiaomi/mimo-v2.6-flash-20260921"
provider_name
"DeepInfra"
status
200
total_cost
0.00024458
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
555
68.33%
Dialogue to Total Word Ratio
Ratio: 72.76%, Deviation: 2.76%
neededClean
false
wordsTotal
558
wordsDialogue
406
34.1643%