NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ6ZHFXSC7YRS4GW7V1F17XS
Run Details
Model:
Qwen 3.5 Plus (2026-04-20)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
51.2s
Cost:
$0.008104
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
97.63%
Matches word count
(details)
84.46%
Dialogue to Total Word Ratio
(details)
91.0456%
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 tapped the blueprints drawn in crayon. "Bill, pass me the grappling hook made of tangled headphones." "Why headphones? We're stealing toys from a six-year-old, not hacking the Pentagon." "Listen, the birthday boy has an iPhone and a security system that detects loud noises. We need stealth." "He has a Golden Retriever named Biscuit." "Biscuit is the real threat. He's seen things. So, the plan: I disguise as the magician. You're the clown?" "I'm not wearing the red nose again. Last time I got peppered and sneezed into a vat of fondue." "Fine, you're the balloon artist. We create a distraction with a 'magic' rabbit that runs toward the presents, grab the loot, and exit via the bouncy castle." "The bouncy castle is inflatable. We'll bounce straight into the neighbor's pool." "Exactly! Wet, confused thieves are less suspicious than dry ones holding a mountain of Lego." "That's... actually surprisingly sound. Hand me the nose. I have a squeaky exit to practice." "And Bill? Don't touch the Star Destroyer until the extraction point." "I'm a professional! ...Mostly. Just don't blame me if the rabbit steals the show." "We're here for the plastic gold, Bill."
created_at
"2026-04-27T08:05:24.543Z"
4/27/2026, 8:05:24 AM
model
"qwen/qwen3.5-plus-20260420"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
671
moderation_latency
(null)
generation_time
51092
tokens_prompt
77
tokens_completion
3277
native_tokens_prompt
76
native_tokens_completion
3364
native_tokens_completion_images
(null)
native_tokens_reasoning
3076
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
0.008104
router
(null)
provider_responses
0
endpoint_id
"8b4a0fbb-6705-4f8d-a7f1-ad18ecc0edbc"
id
"chatcmpl-8eca68cc-c72b-91d7-9eba-d6d047c11109"
is_byok
false
latency
671
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-1777277124-BCpqx7zQMHPbcJIDRs7j"
session_id
(null)
api_type
"completions"
id
"gen-1777277124-nXkFwaue7ji9hqCpOHON"
upstream_id
"chatcmpl-8eca68cc-c72b-91d7-9eba-d6d047c11109"
total_cost
0.008104
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
97.63%
Matches word count
n/a
neededClean
false
words
193
84.46%
Dialogue to Total Word Ratio
Ratio: 96.41%, Deviation: 6.41%
neededClean
false
wordsTotal
195
wordsDialogue
188
91.0456%