NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M36WJ0CH62FRZXKF4PM5NYVJ
Run Details
Model:
Xiaomi MIMO v2.6 Pro
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
24.2s
Cost:
$0.000623
Provider:
Xiaomi
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0000%
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 spread the blueprint across the café table and Bill leaned in so close his nose nearly touched the paper. "So here's the kitchen," Molly said, tapping the corner. "Catering staff go in and out every fifteen minutes. That's our window." "Window." Bill squinted. "Pun intended?" "Focus, Bill." "Fine. But the birthday kid's mom hired security. A security guard. At a seven-year-old's party." "He's there to watch the bounce house, not the gift table." "How do you know?" "Because I talked to him yesterday. Lovely man named Terry. He told me he's terrified of clowns, so all I have to do is—" "Wait, you hired a clown?" "I booked one through the caterer's contact list. It's already paid for. The clown arrives at four, Terry panics, wanders off toward the parking lot, and we walk right in." Bill sat back and folded his arms. "We're robbing a child's birthday party. I want you to hear yourself." "I hear myself perfectly. There are two dozen presents on that table and every single one is wrapped in visible, untraceable cash under the wrapping." "The parents give cash to a seven-year-old?" "Molly pulled out her phone and showed him the e-vite. The RSVP screen listed the gift registry at a high-end toy store. Every gift on that table cost at least a hundred bucks, and gift receipts are tucked in each card." "So we take them, exchange them, cash out." "Twelve grand minimum." Bill exhaled slowly. "And the kids?" "What about them?" "The kids, Molly. Children. Small humans who will be upset." "Bill, I promise you, that seven-year-old has thirty cousins and will not notice six or seven missing presents." "Six or seven? We're leaving some behind?" "We leave the ugly ones. It would be suspicious if the whole table were empty. We stage it like some older kids grabbed a few and nobody bats an eye." Bill studied her for a long moment. "The clown thing is really good." "Thank you." "But if Terry catches us, I'm telling him your name." "Understood." Molly slid the blueprint back into its tube. "Wear something colorful. It's a party." "Disguise as a parent." "Disguise as a fun uncle who arrived late. Carry a balloon if it helps." "I don't even like kids." "Then smile less. That actually helps more." Bill drummed his fingers on the table. "What time do we meet?" "Three-thirty. We do the clown handoff, slip in through the kitchen, grab the bags from the gift table while they're doing cake, and we're out before anyone sings the second verse of Happy Birthday." "Nobody sings two verses." "Exactly. We'll already be gone."
created_at
"2026-09-23T10:21:37.558Z"
9/23/2026, 10:21:37 AM
model
"xiaomi/mimo-v2.6-pro-20260921"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1125
moderation_latency
(null)
generation_time
24129
tokens_prompt
75
tokens_completion
741
native_tokens_prompt
71
native_tokens_completion
681
native_tokens_completion_images
(null)
native_tokens_reasoning
79
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
0.000623355
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790158897-9qIpdQ26YsjggaIv1ynb"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790158897-woZ3SuA2yn8xLKPjJ4jK"
upstream_id
"956f1347-1b89-4208-8b87-8069563f0970_071f37d1b15c4608876f68f3d9288a12"
provider_responses
0
endpoint_id
"2605413e-4a82-494f-ba65-d75f37ac3f11"
is_byok
false
latency
70
model_permaslug
"xiaomi/mimo-v2.6-pro-20260921"
provider_name
"DeepInfra"
status
429
1
endpoint_id
"4354fc36-b8ab-4ced-aa8c-0efb6b4523f1"
id
"956f1347-1b89-4208-8b87-8069563f0970_071f37d1b15c4608876f68f3d9288a12"
is_byok
false
latency
1045
model_permaslug
"xiaomi/mimo-v2.6-pro-20260921"
provider_name
"Xiaomi"
status
200
total_cost
0.000623355
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
0.00%
Matches word count
n/a
neededClean
false
words
439
0.00%
Dialogue to Total Word Ratio
Ratio: 86.80%, Deviation: 36.80%
neededClean
false
wordsTotal
447
wordsDialogue
388
0.0000%