NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M36W800VPJBMTE5MS51DQT11
Run Details
Model:
Xiaomi MIMO v2.6 Pro
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
32.2s
Cost:
$0.000695
Provider:
Xiaomi
Evaluation summary
Score
Evaluator
Details Link
1.04%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.5180%
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 spread a colorful napkin across the café table and drew on it with a red crayon she'd swiped from the booth beside her. "Okay, here's the layout of the venue. Balloon arch at the entrance, which we use for cover. Cake table here. Presents here." She stabbed the napkin aggressively. Bill squinted at the drawing. "What's that blob?" "The climbing wall." "There's a climbing wall at a seven-year-old's birthday?" "It's elite, Bill. Very exclusive. Not our problem though. Our problem is the presents." "How much loot are we talking?" "Twelve kids, each bringing a gift. Minimum forty bucks a pop. That's what? Six hundred? Seven?" "Less your discount on the math, so around two hundred." "The math is fine. Focus. Here's the plan. I go in disguised as a clown." "You're kidding me." "I am not kidding you. I rented the costume last week. Big red shoes, rainbow wig, the works. Nobody questions a clown at a children's party. They just assume he's paid to be there." "And what if they didn't hire a clown?" "Then I'm an enthusiastic guest. A really committed uncle. Either way, I blend in." Bill pinched the bridge of your nose. "Okay, and what am I doing while you're making balloon animals and stealing gift bags?" "You're the delivery driver. Wait outside in the van." "We don't have a van." "We have your Honda Civic with the broken window and the bumper sticker that says 'My Other Car Is Also a Disaster.'" "That was a gift from my mother." "Your mother has taste problems. Listen. I go in, do twenty minutes of crowd work, warm up the room. Then I move to the present pile. I take the bags in waves, three or four at a time, hand them off to you at the side entrance." "In full clown face?" "I'll have the makeup on. It's good for anonymity. Once they find the gifts missing, their description of the suspect will be 'the terrifying clown with the enormous red shoes.' The police will never identify me as an actual criminal. They'll think it was the hired entertainment." "What if they catch you mid-grift?" "I cry. Clowns crying is the saddest thing in the world. Even hardened parents will look away. It's built-in emotional camouflage." Bill leaned back. "This is the dumbest plan you've ever had, and you once tried to rob a laundromat with a squirt gun." "The squirt gun worked! We got forty-three dollars in quarters!" "You got chased by a washing machine." "That was a false memory." "It was a treadmill at the gym next door, and a woman named Gladys sat on you until police arrived." Molly waved him off. "Ancient history. We're professionals now. This is a clean job. Three hundred bucks a piece, easy. And think of it, Bill. It's our first job on the party circuit. Weddings, bar mitzvahs, quinceañeras. The gift-heisting market is completely untapped." Bill stared at the napkin map, then at Molly's manic grin. "We're going to prison." "We're going to the Bahamas. With seven-year-olds' presents. Now put on the spare clown nose. I need to test your balloon animal skills."
created_at
"2026-09-23T10:16:09.505Z"
9/23/2026, 10:16:09 AM
model
"xiaomi/mimo-v2.6-pro-20260921"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
927
moderation_latency
(null)
generation_time
32070
tokens_prompt
75
tokens_completion
838
native_tokens_prompt
71
native_tokens_completion
763
native_tokens_completion_images
(null)
native_tokens_reasoning
57
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
0.000694695
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790158569-ASSzFBrIA9i0U1Pla5lU"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790158569-1CJmkDXS2x3iWDDNXr12"
upstream_id
"69e88970-8f29-4a21-801c-e87785cfbbe5_5cb1e721097844bbb5737eb78fc260cc"
provider_responses
0
endpoint_id
"2605413e-4a82-494f-ba65-d75f37ac3f11"
is_byok
false
latency
87
model_permaslug
"xiaomi/mimo-v2.6-pro-20260921"
provider_name
"DeepInfra"
status
429
1
endpoint_id
"4354fc36-b8ab-4ced-aa8c-0efb6b4523f1"
id
"69e88970-8f29-4a21-801c-e87785cfbbe5_5cb1e721097844bbb5737eb78fc260cc"
is_byok
false
latency
844
model_permaslug
"xiaomi/mimo-v2.6-pro-20260921"
provider_name
"Xiaomi"
status
200
total_cost
0.000694695
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
1.04%
Matches word count
n/a
neededClean
false
words
526
0.00%
Dialogue to Total Word Ratio
Ratio: 88.95%, Deviation: 18.95%
neededClean
false
wordsTotal
534
wordsDialogue
475
0.5180%