NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M36TTPP3XKSW23TMTV93EK5S
Run Details
Model:
Xiaomi MIMO v2.6 Pro
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
24.5s
Cost:
$0.000685
Provider:
Xiaomi
Evaluation summary
Score
Evaluator
Details Link
2.01%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
1.0058%
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 pinned the floor plan of the Hendersons' house to the corkboard and smoothed it with both hands. Bill leaned against the doorframe eating a baby carrot like it was a cigar. "Alright, here's the setup," Molly said. "Birthday party, Saturday, two in the afternoon. Eight-year-old kid named Tyler. We go in while everyone's distracted by the cake situation and come out with everything wrapped and bowed on the gift table." "The cake situation," Bill repeated. "Molly, there is always a cake situation at these things. Last week I watched a clown cry behind a porta-potty at a kids' party. These events are chaos. Chaos is our friend." "Fair enough. How many presents are we talking?" "Depends on Tyler's social standing, but I'd estimate fifteen to twenty. Big ones, small ones, at least one that's clearly from a grandmother who doesn't know the kid at all and bought him a bread maker." "Kids don't want bread makers." "Grandma doesn't care. That's the beauty of it. She's operating on a completely different wavelength and we benefit from her confusion." Bill crunched the carrot. "What's the exit strategy?" "We mingle, we position near the gift table, and when they do the piƱata thing, we haul the bags to the van. Simple. Clean." "Molly, we don't have a van." "Then we get a van." "With what money?" "We steal the van first." "We can't steal a van to steal kids' presents. That's just stealing twice and the first one makes the second one worse." "You have a better idea?" "Yeah, I do. We bring trash bags and walk right out the front door. Nobody stops a man with trash bags at a kids' party. They'll think we're cleaning up." "That's not a van, that's just walking with bags." "Walking with bags is its own vehicle, Molly." She stared at him. He stared back, somehow proud of himself. "Fine," she said. "Trash bags. But we wear something that says we work there. Concession stand, event staff, something. I'll get a clipboard." "A clipboard is basically a badge for adults. People see a clipboard and they just assume you're important. I'm on board with the clipboard." "What about disguises?" "What about them?" "We need disguises, Bill. You look like exactly the kind of man who steals presents from children. You have that energy." "Everyone says that." "Because it's true. Put on a Hawaiian shirt and some sunglasses. Look like a dad who wandered in from a barbecue across the street." "I don't look like a dad." "You'll look like whatever I tell you to look like if you want your cut of the bread maker." "Which cut of the bread maker?" "One hundred percent of the bread maker. I don't want it and neither will anyone else. It's the classic heist problem of only stealing things nobody wants." Bill looked at the floor plan. "What about the cake? Can we take the cake?" "Absolutely not." "Why not?" "Because we are professionals, Bill. We steal gifts from children and we have standards." Bill nodded slowly, as if this made perfect sense. "Friday, then. We recon the house." "We recon the house."
created_at
"2026-09-23T09:51:25.385Z"
9/23/2026, 9:51:25 AM
model
"xiaomi/mimo-v2.6-pro-20260921"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1511
moderation_latency
(null)
generation_time
24446
tokens_prompt
75
tokens_completion
843
native_tokens_prompt
71
native_tokens_completion
752
native_tokens_completion_images
(null)
native_tokens_reasoning
61
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
0.000685125
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790157085-9e7JBEIq8QKmUpNzUeY7"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790157085-PRgffXdFJPh2RzCPKF9h"
upstream_id
"d2f38cfc-d891-4241-a5d3-416b2269c4c5_805323bca48f4197ac42a9c4be40c852"
provider_responses
0
endpoint_id
"4354fc36-b8ab-4ced-aa8c-0efb6b4523f1"
id
"d2f38cfc-d891-4241-a5d3-416b2269c4c5_805323bca48f4197ac42a9c4be40c852"
is_byok
false
latency
1435
model_permaslug
"xiaomi/mimo-v2.6-pro-20260921"
provider_name
"Xiaomi"
status
200
total_cost
0.000685125
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
2.01%
Matches word count
n/a
neededClean
false
words
525
0.00%
Dialogue to Total Word Ratio
Ratio: 89.20%, Deviation: 19.20%
neededClean
false
wordsTotal
528
wordsDialogue
471
1.0058%