NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-25-01KJBFZ9XW6ZSHGJJMPCQTKT4B
Run Details
Model:
Qwen 3.5 27B
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
1m 54s
Cost:
$0.027407
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9995%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 spread blueprints across the sticky diner table. She tapped a circle near the bounce house with a gloved finger. The air smelled of old coffee. Bill adjusted his fake mustache very nervously. He looked around the empty booth for witnesses. "The security is laughable," Molly said. "Just a guy with a clipboard." Bill looked at the sugar packets. "And the loot? You sure it's worth the risk?" "Think about the Lego sets," Molly replied. "We hit the buffet first." Bill looked at the sugar packets. "What about the parents?" "They watch the clown," Molly assured him. "We vanish before the cake arrives." Bill nodded slowly. He held the crowbar. He waited for a signal. "Okay. But what if a kid catches us?" "Then we say we are the gift inspectors," Molly grinned. "They love tuxedos." Bill laughed softly. "You are crazy. But I am in." Molly checked her watch. Time was ticking. The clock ticked loudly. "Good. Ten minutes." "Do we take the cake?" Bill asked. "No cake," Molly said firmly. "Too much frosting." "Right. Just the presents." "Exactly," Molly confirmed. "Let's make kids cry." Bill stood up. "I hope they have batteries." "They always do," Molly said. "Now move."
created_at
"2026-02-25T22:51:02.977Z"
2/25/2026, 10:51:02 PM
model
"qwen/qwen3.5-27b-20260224"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
426
moderation_latency
(null)
generation_time
114111
tokens_prompt
77
tokens_completion
8582
native_tokens_prompt
76
native_tokens_completion
11410
native_tokens_completion_images
(null)
native_tokens_reasoning
11109
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
0.0274068
router
(null)
provider_responses
0
endpoint_id
"f3f88554-0c22-4d57-973b-0dec948808e8"
id
"chatcmpl-a6aecb2a-6e89-9cae-b51b-acdd4d1c6160"
is_byok
false
latency
426
model_permaslug
"qwen/qwen3.5-27b-20260224"
provider_name
"Alibaba"
status
200
api_type
"completions"
id
"gen-1772059862-fSO4zD80iBmL5OebQ9UB"
upstream_id
"chatcmpl-a6aecb2a-6e89-9cae-b51b-acdd4d1c6160"
total_cost
0.0274068
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
201
100.00%
Dialogue to Total Word Ratio
Ratio: 50.25%, Deviation: 0.25%
neededClean
false
wordsTotal
201
wordsDialogue
101
99.9995%