NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M36WF4M0360KDNRYMQEZ3DPX
Run Details
Model:
Xiaomi MIMO v2.6 Pro
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
24.0s
Cost:
$0.000661
Provider:
Xiaomi
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.3562%
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
Molly pinned the hand-drawn floor plan to the motel wall and traced a circle around the living room. Bill studied it with the intensity of a surgeon reading X-rays. "All the presents will be piled right here, next to the cake table," she said. "How many kids are we talking?" "Fourteen confirmed guests, ages four to eight." "Fourteen kids. That's an army." "They're children, Bill." "Children are unpredictable. Have you seen one run? They don't have a natural deceleration zone. They just crash into things." Molly jabbed her pencil at the sketch. "The party runs two to four on Saturday. From two to two forty-five the parents will be sedated by coffee and small talk. The key window is during the magic show at two thirty." "Who's doing the magic show?" "A guy called Dazzling Dan. He does card tricks and pulls scarves from somewhere unfortunate. He'll have every kid hypnotized." "And the parents?" "Dazzling Dan has this thing where he pretends to read minds and reveals your worst secret. Trust me, the adults will be frozen in secondhand embarrassment." Bill leaned back on the motel bed and laced his fingers behind his head. "Walk me through the entry again." "Back door through the kitchen. The mom is three espressos deep by noon and won't lock it until after the cake cutting." "That seems irresponsible." "It's a child's birthday, Bill, not a federal building." "Still. Weak point. But fine. And the presents?" "I slip out during the magic show while everyone's looking at Dazzling Dan and his suspiciously floppy sleeves. I grab the gift bags first, then the boxes. The big one in the red paper is probably a tricycle. We'll need to break that down outside." "You're going to disassemble a tricycle in someone's backyard?" "Behind the shed." "Behind the shed," he repeated slowly. "Behind the shed, Bill. There's a lilac bush. Nobody looks at lilac bushes." He pulled up a photo on his phone of a pastel-bow-covered loot from a baby shower. "Last time you said the same thing about a birdbath, and I got dive-bombed by a finch." "That finch was small." "That finch was relentless. It had an attitude problem." Molly sat down across from him and folded the floor plan neatly in half. "We hit the tricycle first because it's the heaviest and I want it gone before I start the smaller items. Gift bags go into the duffel. We leave through the side gate and meet at the van on Elm." "The van that doesn't lock on the passenger side?" "The van that has a blanket over the seat, yes." "Sometimes I think you plan failures for the thrill." Molly smiled and tucked the floor plan into her jacket pocket. "I plan victories that just happen to have personality. Saturday. Two thirty. Bring gloves. The wrapping paper has glitter on it and glitter is essentially a crime scene waiting to happen." Bill nodded slowly, already dreading the glitter.
created_at
"2026-09-23T10:20:03.59Z"
9/23/2026, 10:20:03 AM
model
"xiaomi/mimo-v2.6-pro-20260921"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1170
moderation_latency
(null)
generation_time
24007
tokens_prompt
75
tokens_completion
813
native_tokens_prompt
71
native_tokens_completion
724
native_tokens_completion_images
(null)
native_tokens_reasoning
73
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
0.000660765
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790158803-dIbsHN0WZ8EQ7i4FcXW9"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790158803-FnF0LaQ2uRw5A40icSH5"
upstream_id
"0a73b869-9e96-41d3-9840-d7cdb95995b0_96375f0dad344c969cb2df594387c7a4"
provider_responses
0
endpoint_id
"4354fc36-b8ab-4ced-aa8c-0efb6b4523f1"
id
"0a73b869-9e96-41d3-9840-d7cdb95995b0_96375f0dad344c969cb2df594387c7a4"
is_byok
false
latency
1088
model_permaslug
"xiaomi/mimo-v2.6-pro-20260921"
provider_name
"Xiaomi"
status
200
total_cost
0.000660765
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
98.71%
Matches word count
n/a
neededClean
false
words
494
0.00%
Dialogue to Total Word Ratio
Ratio: 78.76%, Deviation: 28.76%
neededClean
false
wordsTotal
499
wordsDialogue
393
49.3562%