NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ709V590XETJ2P20KC0KD17
Run Details
Model:
Qwen 3.5 Plus (2026-04-20)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
2m 13s
Cost:
$0.021172
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.3562%
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 Johnson residence blueprint, her nose twitching as balloon latex and desperation filled the cramped van. Bill adjusted his strangling tie, eyes darting between the target house and a crumbled granola bar. This job demanded precision, silence, and absolute indifference toward glitter-wrapped plastic treasures meant for weeping toddlers. He pointed a trembling finger at the patio doors, mimicking a stealthy creep until his elbow knocked over a thermos with a clatter resembling a dropped anvil. Molly hissed through gritted teeth, forcing oversized clown shoes onto her feet for a noiseless approach, though the squeaking rubber mocked every weight shift. The clock neared the magic hour when cake cutting would clear the room. Bill checked his utility belt, swapping a lockpick for a juice box, while Molly practiced an innocent smile in the side mirror, an expression so unsettling it made the streetlamp flicker. They were ready to trade kindergarten joy for pawn shop cash and ruined reputations. Bill gripped his satchel handle, swallowed hard, and rasped the critical instructions for the shameful crusade with a voice trembling like a leaf in a hurricane. "Grab the toys and run before Mom wakes up. Secure the presents immediately. Avoid the squeaky floorboards. Van is idling. Move."
created_at
"2026-04-27T08:18:42.479Z"
4/27/2026, 8:18:42 AM
model
"qwen/qwen3.5-plus-20260420"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
695
moderation_latency
(null)
generation_time
132824
tokens_prompt
77
tokens_completion
7481
native_tokens_prompt
76
native_tokens_completion
8809
native_tokens_completion_images
(null)
native_tokens_reasoning
8540
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
0.021172
router
(null)
provider_responses
0
endpoint_id
"8b4a0fbb-6705-4f8d-a7f1-ad18ecc0edbc"
id
"chatcmpl-f815e35e-8f75-9a69-846c-6434fe0544cb"
is_byok
false
latency
695
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-1777277922-PHFh6kst3NxpfcrIit5K"
session_id
(null)
api_type
"completions"
id
"gen-1777277922-HCxIXnTcitpfu5gXmpqT"
upstream_id
"chatcmpl-f815e35e-8f75-9a69-846c-6434fe0544cb"
total_cost
0.021172
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
98.71%
Matches word count
n/a
neededClean
false
words
206
100.00%
Dialogue to Total Word Ratio
Ratio: 10.14%, Deviation: 0.14%
neededClean
false
wordsTotal
207
wordsDialogue
21
99.3562%