NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHK38E08KSGP1F1FM1THZEZY
Run Details
Model:
Qwen 3.5 397B A17B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
4m 41s
Cost:
$0.036823
Provider:
Alibaba
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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 peeked. "See the target?" Bill adjusted his mask. "It's a bouncy castle." "It's a goldmine, Bill. Wrapped Lego, plushies, cash envelopes." "They're six, Molly. Actual six-year-olds." "Exactly. Zero security awareness. Parents are drunk on punch." "I feel physically sick." "Focus. You take the piƱata loot. I'll grab the main table." "What about the clown?" "Balloon animals aren't a threat." "He knows moves, Mol. Twisting skills imply combat training." "Just disable the music box. That's the alarm system." "And the goody bags?" "Leave the plastic whistles. Take the candy." "Wait, is that a pony?" "Live asset? High risk." "I can't steal a pony." "Ride it out. Distraction tactic." "You're insane." "I'm wealthy. Go." Bill sighed. "Fine. But I'm keeping the shiny wrapper." "Move." They crawled forward. "Do we have getaway vehicles?" "Minivans. Stealth mode." "Sliding doors?" "Obviously." "Tinted windows?" "Yes." "Engine running?" "Always." "Good." "What about security cameras?" "Parents phones. Don't flash." "Okay. Let's rob some toddlers." "Finally." "Any guards?" "Just moms." "Scary moms?" "Very." "Weapons?" "Sharpened strollers." "Noted." "Go time." "Timer set?" "Five minutes." "Plenty." "Ready?" "Born ready." "Let's roll." "What now?" "Forgot the cake." "Leave it." "But it's really chocolate." "Priorities, Bill." "Alright. Fine." "Okay. Move out."
created_at
"2026-02-16T11:31:45.271351+00:00"
2/16/2026, 11:31:45 AM
model
"qwen/qwen3.5-397b-a17b-20260216"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2704
moderation_latency
(null)
generation_time
280606
tokens_prompt
77
tokens_completion
8352
native_tokens_prompt
76
native_tokens_completion
10216
native_tokens_completion_images
(null)
native_tokens_reasoning
9795
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.0368232
router
(null)
provider_responses
0
id
"chatcmpl-f4556c73-7f1c-9d92-b6e3-d52472f8b205"
status
200
is_byok
false
latency
2704
endpoint_id
"180484a2-e24b-495a-ba41-b34b680d5a9f"
provider_name
"Alibaba"
model_permaslug
"qwen/qwen3.5-397b-a17b-20260216"
api_type
"completions"
id
"gen-1771241224-vhRloNCSpit0KehK2YNh"
upstream_id
"chatcmpl-f4556c73-7f1c-9d92-b6e3-d52472f8b205"
total_cost
0.0368232
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
Evaluation details
Result
Evaluator
Details
Meta Data
99.9990%
Matches word count
n/a
neededClean
false
words
201
95.8858%
Dialogue to Total Word Ratio
Ratio: 94.53%, Deviation: 4.53%
neededClean
false
wordsTotal
201
wordsDialogue
190
97.9424%