NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M36VCPVPFKXENKM0VT5AHC6J
Run Details
Model:
Xiaomi MIMO v2.6 Flash
Test:
Dialogue tags
Scenario:
Write 500 words with 30% dialogue
Duration:
33.5s
Cost:
$0.000212
Provider:
Xiaomi
Evaluation summary
Score
Evaluator
Details Link
95.99%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
47.9934%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 30% 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
The back alley behind the community center smelled of rotten cabbage and burnt hot dogs, but Molly had seen worse. She pressed a crumpled floor plan against the damp brick wall and squinted at it under the jaundiced glow of a fire escape light. "Okay, listen up. The party starts at two. That gives us exactly forty minutes to breach, grab, and disappear." Bill chewed on his thumbnail. "What if there's a guard?" "There's no guard, Bill. It's a six-year-old's birthday party." "Yeah, but what if they hired one? Like a bouncer dressed as Spider-Man?" Molly exhaled through her nose. "They didn't hire a bouncer. Now shut up and look at the plan. We enter through the rear kitchen. Past the snack table. Through the rec room. Presents are stacked against the east wall under a big My Little Pony banner." Bill studied the drawing. It looked more like a child's scribble than a tactical map. "Molly, what's the circle with the X?" "That's the cake. Avoid it. Last thing we need is frosting on the getaway coats." "Right, right." Bill tugged at his leather jacket. "And the exit?" "We go back the way we came. Simple. In, grab, out. Two minutes tops." "That's ambitious." "Three minutes then. But not four. If they do a present count before we're three blocks away, we're finished." Bill nodded slowly, though his expression said he had questions. "What do we do with the loot? Somebody's grandma is going to notice her gift to little Timmy is missing." "That's not our problem. We fence them through Danny's shop on Fifth. Transformers, Lego sets, cash. Danny's been moving children's merchandise for years. He's practically a specialist." "He's got an arrest record that reads like a children's literature bibliography." "And that's why he's perfect." Molly folded the plan into quarters and tucked it into her boot. "Now, costumes. The theme is dinosaurs, so we wear dinosaur masks. If anyone sees us, we're just two weird party guests. We blend in." Bill pulled a lumpy green T-Rex mask from his bag and held it up. His eye poked through a jagged hole near the jaw. "This thing looks like it was made in a home economics class." "Better than nothing. Put it on when we go in. Keep your head low, your eyes on the presents, and for God's sake don't speak." "What if a kid talks to me?" "Growl." Bill tried it. "Rrr." "That was pathetic. Practice in the car." Molly straightened and surveyed the alley one final time. A cat knocked over a tin can somewhere in the darkness, and they both flinched before exchanging a shameless look. "Two o'clock," she said, pushing off the wall. "Be ready." Bill followed, already rehearsing his roar under his breath. Somewhere inside the center, a children's song played softly through the walls, and Molly allowed herself the faintest grin. This was going to be the easiest job of her career. She just had to keep Bill from tripping over his own feet on the way out.
created_at
"2026-09-23T10:01:15.39Z"
9/23/2026, 10:01:15 AM
model
"xiaomi/mimo-v2.6-flash-20260921"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2055
moderation_latency
(null)
generation_time
33512
tokens_prompt
75
tokens_completion
789
native_tokens_prompt
71
native_tokens_completion
722
native_tokens_completion_images
(null)
native_tokens_reasoning
42
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
0.0002121
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790157675-QJ6jjgsPOSsBc0RqCchW"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790157675-tuC94o5Z2h8IfvXqX9v3"
upstream_id
"9f5137c1-f398-41d9-a835-2091ba0f5e4c_3f5a359e9d604133bdcfb5294a4ecc74"
provider_responses
0
endpoint_id
"6f7ea660-c5e2-492e-8a39-ec254953b3ae"
id
"9f5137c1-f398-41d9-a835-2091ba0f5e4c_3f5a359e9d604133bdcfb5294a4ecc74"
is_byok
false
latency
1958
model_permaslug
"xiaomi/mimo-v2.6-flash-20260921"
provider_name
"Xiaomi"
status
200
total_cost
0.0002121
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
95.99%
Matches word count
n/a
neededClean
false
words
508
0.00%
Dialogue to Total Word Ratio
Ratio: 58.12%, Deviation: 28.12%
neededClean
false
wordsTotal
511
wordsDialogue
297
47.9934%