NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-25-01KJBDT5FCHYQGZ8E9R2SQPQWF
Run Details
Model:
Qwen 3.5 27B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
1m 19s
Cost:
$0.021023
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
87.84%
Dialogue to Total Word Ratio
(details)
93.9223%
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 mask. "So, the target is the birthday boy's pile?" Bill checked his watch. "Exactly. Unopened Lego sets, action figures, the works." "Parents are distracted by the cake?" "Dad's cutting, Mom's taking photos. Window." "How do we get in?" "Back door. Unlocked. Kids left it open for the cat." "The cat?" "Yes, the cat. It's a golden retriever." "And the exit?" "Dumpster behind the house. We blend in with the trash." "We're stealing presents to blend in with trash?" "We sell them later. Tonight we just need the goods." "What if the mom asks for ID?" "We're wearing clown noses." "Clown noses?" "It's a clown party. Nobody suspects the clowns." "I hate clown noses." "Think of the profit." "Okay. When do we move?" "Now. The cake is being sliced." "Do we take the piƱata?" "Only if it's full." "What about the security guard?" "He's sleeping." "Is he?" "Yes." "After you." "After you." "You're right. I'll go first." "Don't trip on the balloon." "I won't. I'm a pro." "You tripped last week." "That was a rug." "Same difference." "Wait, is that the music?" "No, that is the alarm." "We're doomed." "Not if we run." "Run where?" "Into the pool."
created_at
"2026-02-25T22:13:17.433Z"
2/25/2026, 10:13:17 PM
model
"qwen/qwen3.5-27b-20260224"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
341
moderation_latency
(null)
generation_time
78675
tokens_prompt
77
tokens_completion
6412
native_tokens_prompt
76
native_tokens_completion
8750
native_tokens_completion_images
(null)
native_tokens_reasoning
8405
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
0.0210228
router
(null)
provider_responses
0
endpoint_id
"f3f88554-0c22-4d57-973b-0dec948808e8"
id
"chatcmpl-32c0b54a-7ff3-9c9a-883f-5632b9f414ca"
is_byok
false
latency
341
model_permaslug
"qwen/qwen3.5-27b-20260224"
provider_name
"Alibaba"
status
200
api_type
"completions"
id
"gen-1772057597-lpN1ICUfvX0bEWQtEMLV"
upstream_id
"chatcmpl-32c0b54a-7ff3-9c9a-883f-5632b9f414ca"
total_cost
0.0210228
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
87.84%
Dialogue to Total Word Ratio
Ratio: 96.00%, Deviation: 6.00%
neededClean
false
wordsTotal
200
wordsDialogue
192
93.9223%