NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-25-01KJBGMTCBCQ6ZBM115DXA4XXJ
Run Details
Model:
Qwen 3.5 27B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
1m 39s
Cost:
$0.023322
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
99.74%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.8722%
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 wig nervously outside. "Are you sure about this, Bill?" Bill checked his expensive watch carefully. "Positive. It is a six-year-old birthday. High value, low security." "The presents?" "Every single one. Legos, dolls, the works." "Won't the parents notice?" "They'll be busy with cake. We hit gift table, vanish." "What about the balloons?" "Leave them. Too much air, little profit." "Okay. How do we get in?" "Back door. It's propped open for the ice cream man." "And out?" "Van. Covered in glitter. Blends with the theme." "Glitter?" "It's a unicorn party, Molly. Glitter is camouflage." "I hate glitter." "You hate getting caught more." "Fair point. What's the signal?" "When the piñata breaks." "If the piñata breaks, everyone runs." "Exactly. Chaos is our friend." "So we wait for the sugar rush?" "We wait for the sugar crash. They'll nap." "Brilliant. I'll bring the duffel." "I'll bring the crowbar." "Crowbar?" "For the gift boxes. Some are taped shut." "You're overthinking it." "I'm underestimating the tape." "Fine. Let's move." "Wait. One more thing." "What?" "Do we keep the cake?" "No. We're thieves, not gluttons." "Right. To party." "To loot." They walked away quietly into night. Bill nodded.
created_at
"2026-02-25T23:02:47.952Z"
2/25/2026, 11:02:47 PM
model
"qwen/qwen3.5-27b-20260224"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
510
moderation_latency
(null)
generation_time
98918
tokens_prompt
77
tokens_completion
7622
native_tokens_prompt
76
native_tokens_completion
9708
native_tokens_completion_images
(null)
native_tokens_reasoning
9350
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
0.023322
router
(null)
provider_responses
0
endpoint_id
"f3f88554-0c22-4d57-973b-0dec948808e8"
id
"chatcmpl-f86f54ac-012e-9db7-95de-ed29b4e082d3"
is_byok
false
latency
509
model_permaslug
"qwen/qwen3.5-27b-20260224"
provider_name
"Alibaba"
status
200
api_type
"completions"
id
"gen-1772060567-j3VRg4cRctEreRDU94ik"
upstream_id
"chatcmpl-f86f54ac-012e-9db7-95de-ed29b4e082d3"
total_cost
0.023322
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
Evaluation details
Result
Evaluator
Details
Meta Data
99.74%
Matches word count
n/a
neededClean
false
words
196
100.00%
Dialogue to Total Word Ratio
Ratio: 89.90%, Deviation: 0.10%
neededClean
false
wordsTotal
198
wordsDialogue
178
99.8722%