NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M36X8X3REMK43ZXJA093HKVB
Run Details
Model:
Xiaomi MIMO v2.6 Flash
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
28.8s
Cost:
$0.000208
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.9996%
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 unfolded the birthday invitation she'd swiped from the mail slot and flattened it on the café table between them. The pink card stock was illustrated with balloons and a cartoon dinosaur. She traced the party details with one painted nail while Bill stirred his coffee and watched her face for the telltale gleam that always meant trouble. "Seven years old. Seven years old, Molly. We are not robbing a seven-year-old's party." "I said children's party. I didn't say the birthday boy was seventy." She tapped the address. "14 Maple Court. Single story, one sliding glass door, and a reputation for keeping valuables near the living room floor. The gift table practically organizes itself." "Valuables? It's a kids' party. We're talking LEGO sets and toy trucks." Molly leaned back and crossed her arms. "Do you know how much a sealed Warhammer box goes for? How about that ugly stuffed bear that costs eighty bucks because someone put a scary brand name on it? Parents are hemorrhaging money over there, Bill." "So we're stealing stuffed animals now. This is the career trajectory you envisioned when you dropped out of accounting." "You were the one who said we needed a low-profile score before the Henderson job." "And you said low-profile would mean a gas station tip jar. This is a birthday party with a bounce house." He paused. "Wait. A bounce house?" "See? You're already in." Bill rubbed his temples. "If I agree, what's the play?" Molly pulled a folded napkin from her purse and opened it. She had drawn a crude floor plan on the back. "I go in dressed as a parent. I blend, I chat, I eat whatever's in that Costco tray of assorted cookies. You go in through the back gate dressed as an event magician." "A magician?" "Top hat, wand, the works. You distract the adults with card tricks while I quietly transfer presents from the gift table into the stroller I'll bring. I leave through the front door with six bags in the seat and tell everyone the birthday boy is having a great time." "Six bags in a stroller?" "Twelve if we push it. I checked the invitation. At least twenty guests confirmed. Average gift value forty dollars." "And if someone recognizes us?" Molly smiled. "You're wearing face paint. I'm holding someone's baby." Bill stared at her for a long moment, then took a slow sip of coffee. "Where do I get face paint?" "Now you're thinking like a professional." She tucked the invitation back into her purse. "This is a rehearsal, Bill. A dress run for something real. We test the skill set, not the stakes." "Right." He finished his coffee and set the cup down. "A dress run." "A dress run." He watched her leave the café with the urgency of a woman who had already set an alarm on her phone. He stared at the cartoon dinosaur on the napkin. Then he pulled out his phone and began searching magicians' supplies.
created_at
"2026-09-23T10:34:08.767Z"
9/23/2026, 10:34:08 AM
model
"xiaomi/mimo-v2.6-flash-20260921"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2119
moderation_latency
(null)
generation_time
27654
tokens_prompt
75
tokens_completion
802
native_tokens_prompt
71
native_tokens_completion
707
native_tokens_completion_images
(null)
native_tokens_reasoning
71
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
0.0002079
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790159648-04pfjFvjOdKN3cJ2kUqt"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790159648-P6sSVujlv2oVexle7vCG"
upstream_id
"chatcmpl-RNFQVL0saI8jlkM8gUtZFqOn"
provider_responses
0
endpoint_id
"8f1a1d4b-adc8-465f-860a-4dc2aad88765"
id
"chatcmpl-RNFQVL0saI8jlkM8gUtZFqOn"
is_byok
false
latency
125
model_permaslug
"xiaomi/mimo-v2.6-flash-20260921"
provider_name
"DeepInfra"
status
200
total_cost
0.0002079
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
100.00%
Matches word count
n/a
neededClean
false
words
499
0.00%
Dialogue to Total Word Ratio
Ratio: 66.40%, Deviation: 16.40%
neededClean
false
wordsTotal
503
wordsDialogue
334
49.9996%