NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-25-01KJBJBS2H9PPAR26FKTCHW2AZ
Run Details
Model:
Qwen 3.5 35B
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
1m 28s
Cost:
$0.029217
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
99.38%
Matches word count
(details)
88.61%
Dialogue to Total Word Ratio
(details)
93.9918%
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 adjusted her latex mask while Bill checked his watch. The dumpster behind the venue smelled like stale cake and desperation. "Are you certain this is the right address?" "The invitation said Under the Sea. That is the venue." Bill sighed loudly in the cold air. "What if there are security guards?" "They will be busy watching the clown juggle flaming torches." Molly kicked open the side door quietly now. The sound of Happy Birthday blared out loudly immediately. "Here we go," Bill murmured under his breath. "Remember, no crying children. Only cash and cashmere." "We are taking the Legos too." "Legos are illegal contraband." "So are we." They crept inside the hall slowly now. "Wait," where is the ladder? "There is no ladder, you idiot." "We are going to fall, Bill." They moved past the tables and chairs slowly. The air felt thick with sugar and tension inside. "We are not going to fall." "We are professionals." Molly stopped walking for a moment now. "I am a professional at whining." Bill nodded slowly. They grabbed the presents. The boxes were heavy. They carried them away. It was good work, guys. They crept out quickly.
created_at
"2026-02-25T23:32:48.855Z"
2/25/2026, 11:32:48 PM
model
"qwen/qwen3.5-35b-a3b-20260224"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
480
moderation_latency
(null)
generation_time
87748
tokens_prompt
77
tokens_completion
10431
native_tokens_prompt
76
native_tokens_completion
14599
native_tokens_completion_images
(null)
native_tokens_reasoning
14332
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
0.029217
router
(null)
provider_responses
0
endpoint_id
"48c1210f-b7d2-4688-a340-f7424fc99d2b"
id
"chatcmpl-7f2d61c7-0876-9f6a-805e-619405e6b5e2"
is_byok
false
latency
480
model_permaslug
"qwen/qwen3.5-35b-a3b-20260224"
provider_name
"Alibaba"
status
200
api_type
"completions"
id
"gen-1772062368-kZhodr4UwTMd6lrUiUhW"
upstream_id
"chatcmpl-7f2d61c7-0876-9f6a-805e-619405e6b5e2"
total_cost
0.029217
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
Evaluation details
Result
Evaluator
Details
Meta Data
99.38%
Matches word count
n/a
neededClean
false
words
195
88.61%
Dialogue to Total Word Ratio
Ratio: 44.10%, Deviation: 5.90%
neededClean
false
wordsTotal
195
wordsDialogue
86
93.9918%