NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ77CHGYHW25WRCPCCFSHQ07
Run Details
Model:
Qwen 3.6 Flash
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
44.4s
Cost:
$0.013919
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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
The velvet drapes smelled of dust and forgotten dreams. Molly adjusted her neon tutu, checking the security feed on her phone. Bill knelt behind the plastic piƱata, testing the tension of his grappling hook made from reclaimed bungee cords. The birthday boy had just blown out forty-seven candles with terrifying accuracy. Their target sat beneath the fake palm tree, from the giant tricycle to that suspiciously lumpy paper. Molly tapped her headset while Bill wiped sweat from his forehead. He checked his watch, then the ceiling vent above the tree. The music swelled into another rendition of a catchy tune. They needed perfect timing. The parents would be distracted by the slice of cake. Molly ran through the extraction route one more time. Bill packed his velvet sacks, already imagining the weight of toys. The clock ticked toward dessert. "Move fast. They never check the recycling." "I'll grab the big ones." "Wait for my signal." "Got it." "Stay low." The background music finally swelled past the birthday chants. Molly quietly raised two fingers toward the main staircase. Bill tightened his strap and stepped into the shadows. They moved like seasoned professionals who had completely abandoned their dignity. Wrapped toys waited.
created_at
"2026-04-27T10:22:30.948Z"
4/27/2026, 10:22:30 AM
model
"qwen/qwen3.6-flash"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
677
moderation_latency
(null)
generation_time
43941
tokens_prompt
77
tokens_completion
6932
native_tokens_prompt
76
native_tokens_completion
9267
native_tokens_completion_images
(null)
native_tokens_reasoning
9013
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
0.0139195
router
(null)
provider_responses
0
endpoint_id
"2435bec9-c808-4f27-9fc8-12f3460d7b66"
id
"chatcmpl-7647ce50-347e-9e3e-b61c-10d5abba24a5"
is_byok
false
latency
677
model_permaslug
"qwen/qwen3.6-flash"
provider_name
"Alibaba"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777285350-gLW68sCvCme6SaDPUNVF"
session_id
(null)
api_type
"completions"
id
"gen-1777285350-v51xuhb23rLVXnAqi3xQ"
upstream_id
"chatcmpl-7647ce50-347e-9e3e-b61c-10d5abba24a5"
total_cost
0.0139195
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
200
100.00%
Dialogue to Total Word Ratio
Ratio: 9.95%, Deviation: 0.05%
neededClean
false
wordsTotal
201
wordsDialogue
20
100.0000%