NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ72ZQRMA6PR4BEBVJPVZ738
Run Details
Model:
Qwen 3.6 35B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
28.4s
Cost:
$0.004638
Provider:
AtlasCloud
Evaluation summary
Score
Evaluator
Details Link
99.74%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.8722%
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 adjusted her velvet sack while Bill scanned the blueprints. Molly, we can't hit the birthday party. The security is too tight. Bill, relax, it's a seven-year-old named Kevin. The only guard is an inflatable dinosaur. But Molly, if we take everything, how will the kid feel? Feelings don't pay the ransom, do they? Besides, I saw the gift table. There's a Switch, a pony, and what looks like a lifetime supply of glow sticks. A pony? We don't have a stable. We'll fence it. It's high yield. What's our entry vector? I'm disguised as a clown named Chuckles. I'll walk right past the bouncer. You're wearing a wig and oversized shoes. You look like a tax auditor having a nervous breakdown. It's camouflage! Nobody suspects the guy who looks like he's about to audit his own soul. Fine, but what's the distraction? You trip the piƱata rope and start a conga line. A conga line? Chaos is my middle name, Bill. Now check the time. Kevin's turning seven in ten minutes. Ten minutes? I haven't even polished my theft boots! Check your pockets now. Move it, Chuckles. Bill shivered, wiping sweat from his balding head.
created_at
"2026-04-27T09:05:37.049Z"
4/27/2026, 9:05:37 AM
model
"qwen/qwen3.6-35b-a3b-20260415"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
796
moderation_latency
(null)
generation_time
28326
tokens_prompt
77
tokens_completion
4358
native_tokens_prompt
76
native_tokens_completion
4792
native_tokens_completion_images
(null)
native_tokens_reasoning
4517
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
0.004637729
router
(null)
provider_responses
0
endpoint_id
"179c6985-3a1c-48f1-a009-9f3e3e402cdd"
id
"cd96f72344074037a9829b2f0561b0e9"
is_byok
false
latency
795
model_permaslug
"qwen/qwen3.6-35b-a3b-20260415"
provider_name
"AtlasCloud"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777280737-H08NoyNxcoBLPhSgdoUc"
session_id
(null)
api_type
"completions"
id
"gen-1777280737-phsmkO1eho1MCFaufiBV"
upstream_id
"cd96f72344074037a9829b2f0561b0e9"
total_cost
0.004637729
cache_discount
(null)
upstream_inference_cost
0
provider_name
"AtlasCloud"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.74%
Matches word count
n/a
neededClean
false
words
196
0.00%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 90.00%
neededClean
false
wordsTotal
198
wordsDialogue
0
49.8722%