NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M36WBJ6TN8X2TJVAR5840G4S
Run Details
Model:
Xiaomi MIMO v2.6 Flash
Test:
Dialogue tags
Scenario:
Write 500 words with 30% dialogue
Duration:
32.6s
Cost:
$0.000386
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 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
Molly spread the blueprints across the hood of their van, squinting at the hand-drawn floor plan as if it were the Rosetta Stone. Bill leaned over her shoulder, chewing on a toothpick with the intensity of a man who had never actually stolen anything before and was now deeply committed to pretending he had. "So the party's at 347 Maple Lane, three o'clock," Molly said, tapping a cheerful bounce house drawn crudely in the backyard. "Forty-two kids, six piƱatas, and a gift table that, if my contacts are right, is stacked with video games, tablets, and a remote-controlled dinosaur." "A remote-controlled dinosaur," Bill repeated. "That's the real target?" "No, the real target is everything. The dinosaur is just the cherry on top." Bill nodded slowly. "What about the parents?" "Distraction. I've arranged for a mime to cause chaos near the kitchen. Well, I hired an actor to pretend to be a mime. He owes me a favor." "A fake mime." "Bill, everything about tonight is a fake mime. We dress up as pizza delivery guys. We walk in, collect the presents like they're leftovers, and walk out. By the time anyone notices, we're three blocks away eating pizza in our van." "I thought we were stealing the presents, not actually delivering pizza." "We're doing both. See, this is why you're here. You're thinking three steps ahead and I'm only thinking two." Bill straightened up and crossed his arms. "What if a kid recognizes us?" Molly raised an eyebrow. "Bill, you are a thirty-six-year-old man with a goatee and a scar shaped like a crescent moon. The oldest kid there is eight. They're not going to recognize you." "What if the mime doesn't show up?" "He will. I told him there'd be cake." They sat in silence for a moment, the van's engine ticking softly as it cooled. A dog barked somewhere in the neighborhood. Bill pulled out a crumpled piece of paper from his jacket pocket and smoothed it against the windshield. "I've made a timeline," he said proudly. Molly glanced at it. "Bill, this says two o'clock." "Two o'clock is when we park. Two fifteen, we change costumes. Two thirty, we case the house. Three o'clock, we execute. Four o'clock, we're gone." "That's a lot of optimism for someone who hasn't stolen a thing." "I'm a planner, Molly. You're the muscle. I'm the brains. That's the dynamic." Molly snorted. "You once got lost in a parking garage." "That was a structural design flaw, not a personal failing." She rolled up the blueprints and tucked them into her bag. "Alright. Let's get dressed. Those forty-two children aren't going to rob themselves." Bill grinned, cracking his knuckles. "I've always wanted to be a pizza guy." "You'll be the best one they've never seen."
created_at
"2026-09-23T10:18:06.432Z"
9/23/2026, 10:18:06 AM
model
"xiaomi/mimo-v2.6-flash-20260921"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2254
moderation_latency
(null)
generation_time
32595
tokens_prompt
75
tokens_completion
1471
native_tokens_prompt
71
native_tokens_completion
1343
native_tokens_completion_images
(null)
native_tokens_reasoning
712
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
0.00038598
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790158686-3jMCNBSAOJHqxg0hhPlB"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790158686-ENBGrUZ2tIEXqQ2dEsan"
upstream_id
"e2869f23-b8cf-49e5-a05f-08056ddbfdcd_23493969bba0493a9ddac088ad3a58ef"
provider_responses
0
endpoint_id
"6f7ea660-c5e2-492e-8a39-ec254953b3ae"
id
"e2869f23-b8cf-49e5-a05f-08056ddbfdcd_23493969bba0493a9ddac088ad3a58ef"
is_byok
false
latency
2178
model_permaslug
"xiaomi/mimo-v2.6-flash-20260921"
provider_name
"Xiaomi"
status
200
total_cost
0.00038598
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
0.00%
Matches word count
n/a
neededClean
false
words
462
0.00%
Dialogue to Total Word Ratio
Ratio: 68.51%, Deviation: 38.51%
neededClean
false
wordsTotal
470
wordsDialogue
322
0.0000%