NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-25-01KJBJH93YC05YHHB32MVCR8M5
Run Details
Model:
Qwen 3.5 Flash
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
1m 58s
Cost:
$0.005644
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
93.65%
Matches word count
(details)
96.68%
Dialogue to Total Word Ratio
(details)
95.1661%
Overall
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 adjusted her tinfoil hat. "Okay. Truck is arriving. We strike when the candle blows, not before we eat." "Wait. Children? Stealing presents from kids is our brand now? What if a small cat sees us run? Or a puppy?" "Only high-value loot. The robot or giant doll. We keep cash but leave stickers on the cards." "Is it legal? We might go to jail for this crime. Cops really love Christmas morning." "Law of the jungle, Bill. Jungle of playdates. Rules differ in the jungle." "You feel dirty?" "I feel terrible. I used to shoplift cereal bars when I was very young indeed." "Different scale. This is heartbreak. The parents will cry when they see the empty box space clearly." "Paper will rip. Be surgical. Use scissors carefully." "We take whole box, paper included. Looks better for us very quickly." "What about parents? They know it is missing." "Blame wind or maybe the dog. Or a bad dream. They will never know forever." "Hush. Cake is cut. It is time now." "On three?" "No. On two. Make it really snappy." "Three, two, one. Go! Run fast now!" They ran and crashed into a piñata. "Ouch! My knee hurts." "Toys in bag. Go now." "Let’s go before singing starts."
created_at
"2026-02-25T23:35:49.126Z"
2/25/2026, 11:35:49 PM
model
"qwen/qwen3.5-flash-20260224"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
524
moderation_latency
(null)
generation_time
117986
tokens_prompt
77
tokens_completion
11338
native_tokens_prompt
76
native_tokens_completion
14092
native_tokens_completion_images
(null)
native_tokens_reasoning
13775
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
0.0056444
router
(null)
provider_responses
0
endpoint_id
"5f6b71b5-8672-4b27-8b2d-f674429f9e63"
id
"chatcmpl-b1a100b7-3fe5-932a-b8da-b559208a97cf"
is_byok
false
latency
524
model_permaslug
"qwen/qwen3.5-flash-20260224"
provider_name
"Alibaba"
status
200
api_type
"completions"
id
"gen-1772062549-TEgcUPONjJ1mWrO14TIT"
upstream_id
"chatcmpl-b1a100b7-3fe5-932a-b8da-b559208a97cf"
total_cost
0.0056444
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
Evaluation details
Result
Evaluator
Details
Meta Data
93.65%
Matches word count
n/a
neededClean
false
words
209
96.68%
Dialogue to Total Word Ratio
Ratio: 94.29%, Deviation: 4.29%
neededClean
false
wordsTotal
210
wordsDialogue
198
95.1661%