NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M36TYBVXWDWQZAPG5E7YGAB6
Run Details
Model:
Xiaomi MIMO v2.6 Flash
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
45.8s
Cost:
$0.000217
Provider:
Xiaomi
Evaluation summary
Score
Evaluator
Details Link
75.16%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
37.5778%
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 slid the blueprint across the café table and jabbed a finger at it. "Alright, pay attention. The party's at 143 Maple Drive. Fourteen kids, two sets of grandparents, one dog, and a bounce house." Bill squinted at the paper. "A bounce house? That's a problem. That's a massive inflatable witness." "The kids will be distracted, Bill. Cake. Presents. Whatever garbage they're singing about." "They sing 'Happy Birthday.' You've been to a birthday before, right?" "I've been to parties. Maybe not with matching napkins." "So what's the entry plan?" "Side window of the garage. I counted three steps, then through the laundry room, then straight to the gift table." "Why the garage? Front door's right there." "Because the front door will have a nosy aunt watching it like a hawk. The garage will have laundry detergent and a broken treadmill." "Fair. And the exit?" "Same way, only faster, because by then the dog will have figured out what we're doing." "What about security?" "Just a nanny cam in the corner of the living room. One. It's for watching the kids fight over toys." "One camera. That's insultingly low." "Which makes it perfect." "What's our costume? We need a costume." "I brought lab coats." "Lab coats for a children's party?" "We're the gift inspectors." "They'll be three years old, Molly. The average guest won't know what a gift inspector is, but a parent will ask questions." "We say we're from the manufacturer. A toy safety recall." "We can't fabricate a recall. That's a federal offense." "Bill, we're about to steal presents from toddlers. The least of our problems is a fictional recall." "When you put it that way, lab coats it is." "What about your part? You're on lookout." "I thought you said the dog was the lookout." "The dog's going to the restroom. You're making sure nobody comes through the front door." "And if someone does?" "You pretend to be lost looking for the bathroom." "In a lab coat?" "Everyone pretends to be lost at some point, Bill. It's a human constant." "What's the haul? Do we know the haul?" "Jennifer from the office said her niece got a new tablet, a gift card, and whatever the rich uncle brings. That uncle brings money, Bill." "How much money?" "Enough to skip next month's meetings." "We're not skipping meetings. We don't have meetings. We're criminals." "Exactly. See how that works?" Bill leaned back and cracked his knuckles. "Side window. Lab coats. Gift table. In and out before the cake." "Before the cake, before the candles, before anyone even notices anything's wrong." "And the dog?" "The dog will be too busy with the cake." "Dogs don't eat cake." "Bill, have you met children? Everything ends up on the floor. The dog eats everything." "You've really thought this through." "I think about it every time I drive past that house." "We leave at eight sharp." "We leave at eight sharp."
created_at
"2026-09-23T09:53:25.379Z"
9/23/2026, 9:53:25 AM
model
"xiaomi/mimo-v2.6-flash-20260921"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
956
moderation_latency
(null)
generation_time
35664
tokens_prompt
75
tokens_completion
773
native_tokens_prompt
71
native_tokens_completion
741
native_tokens_completion_images
(null)
native_tokens_reasoning
52
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
0.00021742
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790157205-qOAdBaynJHnd7H8nIAGA"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790157205-gnAi1nFGwrEljvNzYuTQ"
upstream_id
"1e666d08-87f4-4870-96f2-539bb1e945cb_328faa7d8c12433c8d0644d40fdea57b"
provider_responses
0
endpoint_id
"8f1a1d4b-adc8-465f-860a-4dc2aad88765"
is_byok
false
latency
102
model_permaslug
"xiaomi/mimo-v2.6-flash-20260921"
provider_name
"DeepInfra"
status
504
1
endpoint_id
"6f7ea660-c5e2-492e-8a39-ec254953b3ae"
id
"1e666d08-87f4-4870-96f2-539bb1e945cb_328faa7d8c12433c8d0644d40fdea57b"
is_byok
false
latency
856
model_permaslug
"xiaomi/mimo-v2.6-flash-20260921"
provider_name
"Xiaomi"
status
200
total_cost
0.00021742
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Xiaomi"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
75.16%
Matches word count
n/a
neededClean
false
words
487
0.00%
Dialogue to Total Word Ratio
Ratio: 94.66%, Deviation: 24.66%
neededClean
false
wordsTotal
487
wordsDialogue
461
37.5778%