NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ6Z3VCDXMQ3WRQ9H2728FC2
Run Details
Model:
Qwen 3.5 Plus (2026-04-20)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
2m 40s
Cost:
$0.025482
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 smoothed the crumpled invitation across the sticky diner table. The glossy card depicted a cartoon dragon wearing a party hat, which felt deeply personal. Bill traced the backyard perimeter with a grease pencil, mapping their escape route past the inflatable castle and suspiciously unwatched beverage station. They had cracked museum alarms and outrun private security, yet this heist demanded unprecedented finesse. Their target was the premium gift stack, specifically the sealed robotics kits and vintage board games. Parental supervision would inevitably fracture during the cake ceremony, creating a ninety second window of glorious distraction. They would slide beneath the taffeta tablecloths, swap the merchandise for identical crates packed with deflated balloons, and disappear into the afternoon crowd. Bill adjusted his plastic bowtie and finally spoke. "We are absolutely seasoned professionals handling childrens premium loot. Grab the fast one. Move quietly. Stay low. Go now. Please." Molly slid a laminated timeline across the worn vinyl. Sunlight caught the dust. Bill checked his silver watch, noting the precise moment when the bouncy castle attendant would inevitably take a smoke break. They would move with practiced discretion, leaving behind the faint scent of desperation. The plan relied entirely on sugar and screaming.
created_at
"2026-04-27T07:57:57.523Z"
4/27/2026, 7:57:57 AM
model
"qwen/qwen3.5-plus-20260420"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
670
moderation_latency
(null)
generation_time
159720
tokens_prompt
77
tokens_completion
8638
native_tokens_prompt
76
native_tokens_completion
10605
native_tokens_completion_images
(null)
native_tokens_reasoning
10351
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.0254824
router
(null)
provider_responses
0
endpoint_id
"8b4a0fbb-6705-4f8d-a7f1-ad18ecc0edbc"
id
"chatcmpl-ba1a01dd-ff3f-9eae-a028-904dbb41469a"
is_byok
false
latency
670
model_permaslug
"qwen/qwen3.5-plus-20260420"
provider_name
"Alibaba"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777276677-0EvUez93ZuEcmzX6qSaG"
session_id
(null)
api_type
"completions"
id
"gen-1777276677-KKpLOWR4xrIWdQRNY81X"
upstream_id
"chatcmpl-ba1a01dd-ff3f-9eae-a028-904dbb41469a"
total_cost
0.0254824
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
response_cache_source_id
(null)
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%