NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M36SVAZ9PE66P1WEQM5CPA0J
Run Details
Model:
Xiaomi MIMO v2.6 Flash
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
25.8s
Cost:
$0.000206
Provider:
Xiaomi
Evaluation summary
Score
Evaluator
Details Link
90.48%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
45.2423%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 50% 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 night before the heist, Molly and Bill sat across from each other in a diner booth that smelled like old bacon and regret. Molly spread a hand-drawn map across the table, dotted with red X marks and the words PARTY OF THE DECADE scrawled in glitter pen. Bill stared at it for a long moment and then looked up. "So let me get this straight," Bill said. "We're robbing a seven-year-old's birthday party?" "You say 'robbing.' I say 'liberating.'" Molly tapped the map with a plastic fork. "Timmy Harmon has eleven cousins, three family friends, and a grandmother who buys forty-dollar toys. That's easily two thousand dollars in LEGO sets and Nintendo Switch games sitting in that living room." "That's a kindergarten classroom, Molly. There'll be a dozen kids screaming, parents drinking Merlot, a piƱata the size of a horse." "Exactly," Molly said. "Chaos." Bill leaned back and crossed his arms. "Okay, but walk me through the actual plan. Because this map looks like it was drawn by a squirrel." Molly shot him a look. "Phase one. At seven-fifteen, exactly when 'Happy Birthday' starts, I walk in wearing this." She held up a pastel blazer with a plastic apron tied over it. "I'm Linda, the caterer." "And who am I?" "You're my assistant. You wear this." She slid a paper hat across the table. "I'm not wearing a paper hat." "Bill. The hat is essential to the look." Bill picked up the hat, examined it, and set it back down. "Fine. And what do we do once we're inside?" "We collect the gifts. Phase two. While everyone is mesmerized by the cake, I squeeze past the adults near the buffet, and you start bagging the presents from the pile in the corner." "That pile is in full view of like twenty people." "Which is why you'll be moving slow and acting casual. You're wearing the hat. No one suspects a man in a paper hat." Bill rubbed his temples. "This is the worst plan you've ever come up with, and you once tried to steal a statue of a cat from a park." "And we got caught because you sneezed. This time, no sneezing." "What if Timmy asks who I am?" "You say you're Eddie, the assistant caterer. Simple. Clean." Bill squinted at the map again. "What about phase three? You haven't mentioned phase three." Molly grinned and pulled a duffel bag out from under the table. "Phase three is getting out. We leave through the sliding glass door in the backyard. There's a garden shed where we stash the bag. By the time anyone notices the presents are gone, we're at the diner eating pie." Bill looked at the bag, the map, the blazer, and the paper hat. He sighed, picked up the hat, and placed it gently on his head. "When do we go?" he asked. Molly checked her watch. "Tonight. Eight o'clock. Try not to sneeze."
created_at
"2026-09-23T09:34:17.584Z"
9/23/2026, 9:34:17 AM
model
"xiaomi/mimo-v2.6-flash-20260921"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3756
moderation_latency
(null)
generation_time
25807
tokens_prompt
75
tokens_completion
742
native_tokens_prompt
71
native_tokens_completion
700
native_tokens_completion_images
(null)
native_tokens_reasoning
41
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
0.00020594
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790156057-Tk6ffpzlNM6odDXY8n5k"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790156057-W55lGAkHrWuKeNUbs7Zu"
upstream_id
"d7312cc4-07e4-49bc-8f23-9b37df18b8d8_b77d8a19c594453a9656f23a87af461d"
provider_responses
0
endpoint_id
"6f7ea660-c5e2-492e-8a39-ec254953b3ae"
id
"d7312cc4-07e4-49bc-8f23-9b37df18b8d8_b77d8a19c594453a9656f23a87af461d"
is_byok
false
latency
3664
model_permaslug
"xiaomi/mimo-v2.6-flash-20260921"
provider_name
"Xiaomi"
status
200
total_cost
0.00020594
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
90.48%
Matches word count
n/a
neededClean
false
words
490
0.00%
Dialogue to Total Word Ratio
Ratio: 65.25%, Deviation: 15.25%
neededClean
false
wordsTotal
495
wordsDialogue
323
45.2423%