NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-25-01KJBJE4MF1S1XBVH2241C20X9
Run Details
Model:
Qwen 3.5 27B
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
2m 5s
Cost:
$0.031352
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
20.19%
Matches word count
(details)
99.98%
Dialogue to Total Word Ratio
(details)
60.0872%
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
Rain slicked the street as Molly adjusted her grappling hook. Bill checked his kit, butter knife and paperclip. They stood behind a dinosaur hedge, watching the house. Inside, a clown juggled balloons while toddlers screamed. Perfect cover. Molly pulled out a blueprint drawn on a pizza box. Fence was weak, but the dog was a problem. Bill scratched his head, on cap. He looked at colorful boxes through window. They were wrapped in shiny paper. Molly signaled him to move. She wore a black mask. Bill wore a mask saying Smile. They crept toward the side door. Molly tapped the glass. It was locked tight. She sighed, knowing silence required. Bill pulled out a jam jar of glue. He prepared to stick handle open. Molly shook her head at his incompetence. Clown blew a horn. Molly covered her ears. Bill grinned beneath his silly mask. "The clown is a distraction," Molly said. "I really like clowns," Bill replied. "Focus strictly on the loot now please." Molly kicked the door. It swung open instantly. They rushed inside, ready to grab gifts.
created_at
"2026-02-25T23:34:06.228Z"
2/25/2026, 11:34:06 PM
model
"qwen/qwen3.5-27b-20260224"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
433
moderation_latency
(null)
generation_time
124713
tokens_prompt
77
tokens_completion
8939
native_tokens_prompt
76
native_tokens_completion
13054
native_tokens_completion_images
(null)
native_tokens_reasoning
12823
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
0.0313524
router
(null)
provider_responses
0
endpoint_id
"f3f88554-0c22-4d57-973b-0dec948808e8"
id
"chatcmpl-22f0daba-5fe1-993a-8e9e-ab416258eed4"
is_byok
false
latency
433
model_permaslug
"qwen/qwen3.5-27b-20260224"
provider_name
"Alibaba"
status
200
api_type
"completions"
id
"gen-1772062446-XbuyTP0Zsw6mpF8GJqjd"
upstream_id
"chatcmpl-22f0daba-5fe1-993a-8e9e-ab416258eed4"
total_cost
0.0313524
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
Evaluation details
Result
Evaluator
Details
Meta Data
20.19%
Matches word count
n/a
neededClean
false
words
180
99.98%
Dialogue to Total Word Ratio
Ratio: 8.89%, Deviation: 1.11%
neededClean
false
wordsTotal
180
wordsDialogue
16
60.0872%