NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-25-01KJBJJCVN03CHEB6SBP6A2EXB
Run Details
Model:
Qwen 3.5 Flash
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
2m 28s
Cost:
$0.008418
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
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
Molly quietly peered through thick oak branches. The backyard below looked very chaotic. Bill checked his timer, sweat beading on his forehead. This gig was a gamble fueled by debt. The small house glowed with colorful unicorn lights. He nudged her soft elbow pointing at the window near the treehouse. The parents were inside, distracted by cake and punch. She scanned the dark perimeter for motion sensors. The plan was elaborate, involving a distraction about a live snake and fake police siren. The presents were stacked under the tree wrapped in sparkly paper. She adjusted the grappling hook in her left hand, feeling the immense weight of responsibility. They crept very stealthily forward, boots completely silent on the wet brown grass. The very loud noise of the party grew significantly louder, masking their clumsy approach. They scaled the tall wooden fence, aiming directly for the living room windowsill. This was the very big score. The absolute ultimate payday. They quickly lunged for the sill, but a small hand grabbed Molly's ankle. It was the youngest cousin holding a juice box. "Why are we doing this?" "We need the money so badly." "Ready?" "No, I am terrified now," "Just move, Bill."
created_at
"2026-02-25T23:36:25.722Z"
2/25/2026, 11:36:25 PM
model
"qwen/qwen3.5-flash-20260224"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
448
moderation_latency
(null)
generation_time
148018
tokens_prompt
77
tokens_completion
15714
native_tokens_prompt
76
native_tokens_completion
21025
native_tokens_completion_images
(null)
native_tokens_reasoning
20768
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
0.0084176
router
(null)
provider_responses
0
endpoint_id
"5f6b71b5-8672-4b27-8b2d-f674429f9e63"
id
"chatcmpl-99625bfd-f4ef-9fee-aee5-c81bb2a13e92"
is_byok
false
latency
447
model_permaslug
"qwen/qwen3.5-flash-20260224"
provider_name
"Alibaba"
status
200
api_type
"completions"
id
"gen-1772062585-IYveWY8buwPuBizW7ps8"
upstream_id
"chatcmpl-99625bfd-f4ef-9fee-aee5-c81bb2a13e92"
total_cost
0.0084176
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
200
100.00%
Dialogue to Total Word Ratio
Ratio: 10.00%, Deviation: 0.00%
neededClean
false
wordsTotal
200
wordsDialogue
20
100.0000%