NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ78VNCR4A5TPBHGSSR5MBMR
Run Details
Model:
Qwen3.6 Max Preview
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
8m 37s
Cost:
$0.069542
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
98.95%
Dialogue to Total Word Ratio
(details)
99.4754%
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 flattened the crayon blueprint across the sticky diner table. A cold cup of coffee sat between them, entirely forgotten. Bill adjusted his mirrored sunglasses beneath the harsh fluorescent lights. He tapped a calloused finger against the illustrated swing set and exhaled slowly through his nose. "Walk me through the perimeter again, Bill." "Six foot vinyl fence. Gate latch is plastic. I could breach it with a firm sigh." "Good. Entry window is fourteen hundred hours. The magician performs then. All eyes will be on the rabbit. We move during the collective gasp." "What about the clown?" Molly circled a red marker around the driveway. She studied the wax paper markings with clinical detachment. "The clown is a nonfactor. He will be trapped in the balloon industrial complex. His shoes are squeaky. We will hear him coming from three lawns away." "I still think we should neutralize him." "We are not neutralizing a childrens entertainer, Bill. We are professionals. Where is the drop point?" Bill slid a manila folder across the cracked vinyl booth. Inside were grainy photographs of a suburban patio. He aligned the edges perfectly with the table salt shaker. "Behind the bouncy castle. Near the coolers. I scoped it yesterday. Folding table. No security. Just a paper tablecloth with cartoon trains." "Amateur hour. Perfect. How many targets?" "Twenty two kids. Two gifts each. Grandparents are bringing heavy artillery. I saw a tricycle box. We need the duffel and the wagon." "That red wagon squeaks terribly." "I oiled the axles. It glides now. What is the extraction route?" Molly finally met his gaze. She folded her hands like a surgeon reviewing a complicated chart. The diner bell chimed softly as a waitress refilled sugar dispensers nearby. "Through the side gate, past the bushes, into the alley. The van idles there. I painted it to resemble a mobile petting zoo. Nobody questions boxes near a zoo van. They assume it is feed." "Solid. What about the parents?" "Distracted. Mother handles cake logistics. Father mans the grill with a beer and a vacant stare. They will notice nothing until someone asks where the Lego set went." "What about the giant pinata?" "Strictly off limits. That is a structural hazard. We take wrapped goods. We leave the candy donkey. Clear?" "Crystal clear. Do we have a contingency for early cake deployment?" "If they sing early, we abort and blend. I brought hats. You will smile and clap. You will look like a beloved uncle." "I can do that. Should I practice?" "Absolutely not. Remember the timeline. Magician goes up, we go in. Wagon loads, we vanish. We will be three miles away sorting retail value." "This is going to be beautiful, Molly." Bill wiped a stray tear from his cheek. Molly slid the blueprint into her trench coat and stood up. She dropped a five dollar bill onto the checkered tablecloth. "It is a birthday party, Bill. Try not to weep over the metallic paper." "I make absolutely no promises whatsoever, boss."
created_at
"2026-04-27T10:52:51.554Z"
4/27/2026, 10:52:51 AM
model
"qwen/qwen3.6-max-preview-20260420"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3766
moderation_latency
(null)
generation_time
240385
tokens_prompt
77
tokens_completion
9250
native_tokens_prompt
76
native_tokens_completion
8903
native_tokens_completion_images
(null)
native_tokens_reasoning
8217
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"
usage
0.0695422
router
(null)
provider_responses
0
endpoint_id
"ca7fc0c7-f23d-4ac5-b2e0-945be5b61787"
id
"chatcmpl-314569b5-75f1-932c-a12d-ece83a92da1a"
is_byok
false
latency
3766
model_permaslug
"qwen/qwen3.6-max-preview-20260420"
provider_name
"Alibaba"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777287171-4NYKPD5Xc9atSeJFR0qA"
session_id
(null)
api_type
"completions"
id
"gen-1777287171-jnLdD0d3kaWHSR9Qmh3O"
upstream_id
"chatcmpl-314569b5-75f1-932c-a12d-ece83a92da1a"
total_cost
0.0695422
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
501
98.95%
Dialogue to Total Word Ratio
Ratio: 70.46%, Deviation: 0.46%
neededClean
false
wordsTotal
501
wordsDialogue
353
99.4754%