NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M36VQBRRGG5JWDVQ9A6NM92X
Run Details
Model:
Xiaomi MIMO v2.6 Flash
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
43.0s
Cost:
$0.000210
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
60.28%
Matches word count
(details)
1.42%
Dialogue to Total Word Ratio
(details)
30.8465%
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 adjusted the strap of her duffel bag and leaned against the brick wall beside Bill, peering through the chain-link fence at the rainbow-colored balloons bobbing above the Hendersons' backyard. "Alright, listen," Molly whispered. "Mommy Henderson is throwing little Asher his sixth birthday bash. Twenty-six kids. Twelve parents. Three of those kids are absolute chaos agents. And behind the patio doors sits a mountain of gifts. We're going in for every last one." Bill scratched his chin, his enormous mustache twitching nervously. "Every last one? Molly, last time you said that, we ended up with a pinecone in a tupperware." "That was a tactical error. This time, I've done my homework." She pulled out a crumpled napkin covered in crayon scribbles she'd faked a way onto. "I was inside this morning undercover as a party planner's assistant. I've got the full inventory. Four Lego sets, a Nintendo Switch, two ZhuZhu Pets, one Baby Yoda plush, and something in a box so big it could probably be mistaken for a car battery." Bill's eyes went wide. "The Switch alone is worth three hundred dollars. But what about security? I saw a dog. A big dog." "That's not a security dog, Bill. That's Kevin the Golden Retriever. Kevin will lick you until you forget your own name. He is, in fact, the opposite of security." "So what's the plan?" Bill asked, cracking his knuckles. "We go in at three-fifteen. That's right when they're serving cake. All eyes will be on Asher blowing out his candles, and believe me, those candles are like the size of fingers. It'll take a solid forty-five seconds. That's our window." "Forty-five seconds to get everything?" Bill looked skeptical. "There's going to be wrapping paper everywhere. We'll be swimming through it." "Which is why we're wearing these." Molly produced two bright yellow inflatable inner tubes. "We'll slide across the lawn like bobsled champions. I call them the Gift Gliders." Bill stared at them. "Those are children's pool toys." "They're logistics, Bill." "Fine, fine. What do we do if a parent spots us?" "Simple. You're the clown. I hired you to do balloon animals. You start making a balloon sword, they'll forget they ever saw me." "Hey, I have pride." "Pride doesn't pay the mortgage. Balloon animals do." Bill sighed heavily, pulling a red rubber glove over his hands like a thief in a museum film. "Alright. What about exit strategy?" "Same door. We came in through the side gate, we go out the side gate. Kevin will escort us to freedom because Kevin is a good boy and does not understand concepts like boundaries." "And if the big dog attacks?" "Bill, Kevin does not have an aggressive bone in his body. He once tried to befriend a garden hose." Molly checked her watch. "Fifteen minutes. Get your Game Face on." "My Game Face is always on." "That's adorable. Now grab the Gift Gliders."
created_at
"2026-09-23T10:07:04.48Z"
9/23/2026, 10:07:04 AM
model
"xiaomi/mimo-v2.6-flash-20260921"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1313
moderation_latency
(null)
generation_time
42988
tokens_prompt
75
tokens_completion
781
native_tokens_prompt
71
native_tokens_completion
715
native_tokens_completion_images
(null)
native_tokens_reasoning
47
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
0.00021014
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790158024-3hWAilBk1ABlBwtubxwG"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790158024-yqEB8exovhfhbgR5vbWq"
upstream_id
"chatcmpl-R6BsWNXdHrNYu2MVMvrR552V"
provider_responses
0
endpoint_id
"8f1a1d4b-adc8-465f-860a-4dc2aad88765"
id
"chatcmpl-R6BsWNXdHrNYu2MVMvrR552V"
is_byok
false
latency
73
model_permaslug
"xiaomi/mimo-v2.6-flash-20260921"
provider_name
"DeepInfra"
status
200
total_cost
0.00021014
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
60.28%
Matches word count
n/a
neededClean
false
words
485
1.42%
Dialogue to Total Word Ratio
Ratio: 79.23%, Deviation: 9.23%
neededClean
false
wordsTotal
491
wordsDialogue
389
30.8465%