NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-25-01KJBJP6BSK4Z0KFFGKQRY82S4
Run Details
Model:
Qwen 3.5 Flash
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
1m 8s
Cost:
$0.004886
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
97.69%
Dialogue to Total Word Ratio
(details)
98.8060%
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
"The piƱata is empty. It's all plastic beads and regret," Molly whispered. "We need a distraction." "The uncle wears a tux," Bill said. "He'll see us if we trip over the balloons." Bill puffed his chest. "I'm an acrobat." "I tripped once, landing in a pool. It was incredibly graceful." "We aren't jumping into cash. We enter a sea of tiny humans. They scream. Loudly." "Better than guards. Guards have radios. Kids only have tantrums." "How do we get in? The door is locked." "It isn't," Bill said. "They left it open by the cake." "That is suspicious." "That is our opening," she said. "What is the target? I see only a giant stack of paper." "Under the tree. The big one wrapped in foil." "Is it gold bars hidden inside?" "It's a robot. Just a plastic robot." "Will a robot fit in the duffel bag?" "I'll use the vacuum seal, Bill. It will crush." "I can't believe we are stealing toys from children. This is my line." "A redistribution of joy. Think of the parents. They buy batteries." "I hate joy distribution. It smells like sugar." "Fine. Keep the loot. Watch the punch." "Watch the door."
created_at
"2026-02-25T23:38:30.142Z"
2/25/2026, 11:38:30 PM
model
"qwen/qwen3.5-flash-20260224"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
472
moderation_latency
(null)
generation_time
67691
tokens_prompt
77
tokens_completion
9123
native_tokens_prompt
76
native_tokens_completion
12197
native_tokens_completion_images
(null)
native_tokens_reasoning
11898
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
0.0048864
router
(null)
provider_responses
0
endpoint_id
"5f6b71b5-8672-4b27-8b2d-f674429f9e63"
id
"chatcmpl-9d8ce679-1dbb-9830-a0b7-56a64699cdd3"
is_byok
false
latency
472
model_permaslug
"qwen/qwen3.5-flash-20260224"
provider_name
"Alibaba"
status
200
api_type
"completions"
id
"gen-1772062710-E9VM24V9sarveMSznHdn"
upstream_id
"chatcmpl-9d8ce679-1dbb-9830-a0b7-56a64699cdd3"
total_cost
0.0048864
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
Evaluation details
Result
Evaluator
Details
Meta Data
99.92%
Matches word count
n/a
neededClean
false
words
197
97.69%
Dialogue to Total Word Ratio
Ratio: 93.91%, Deviation: 3.91%
neededClean
false
wordsTotal
197
wordsDialogue
185
98.8060%