NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ73FZ7QDFTJKPD552NYER3W
Run Details
Model:
Qwen 3.6 35B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
34.5s
Cost:
$0.005936
Provider:
AtlasCloud
Evaluation summary
Score
Evaluator
Details Link
9.61%
Matches word count
(details)
93.29%
Dialogue to Total Word Ratio
(details)
51.4515%
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
Did you check the perimeter? Molly whispered, adjusting her glitter camo. "Perimeter? Molly, we're hiding behind a bouncy castle filled with screaming toddlers. The perimeter is a mother named Karen who can smell fear and a half-eaten cupcake." "Right. Focus. The loot?" "The loot is under the tree. Three stacks of brightly wrapped boxes. Most of it looks like plastic junk, but I spotted a sealed Lego set near the back. And possibly a tablet if Billy's dad didn't ruin his luck." "Lego is liquid assets. Tablet is the jackpot. What's the extraction route?" "We slip in through the punch bowl, distract the kids with my signature juggling routine, sweep the gifts into these pillowcases, and bail out the doggy door before the piƱata falls." "You're juggling?" "It's the only way to keep Billy engaged. He loves the ball with the lights. If he laughs, he doesn't ask why I'm wearing a mascot head." "The mascot head is a bad call, Bill. That's how they catch you." "Not the clown mascot. The giant rubber chicken. I'm a chicken, Molly. Chickens are invisible. Don't touch the glitter cake. If you get frosting on the zip-ties, the bag won't close, and we'll be caught with thirty-five pounds of Barbie dolls. I said thirty-five pounds! Move! And if you sneeze, you're on your own. Now!"
created_at
"2026-04-27T09:14:28.989Z"
4/27/2026, 9:14:28 AM
model
"qwen/qwen3.6-35b-a3b-20260415"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
669
moderation_latency
(null)
generation_time
34375
tokens_prompt
77
tokens_completion
4724
native_tokens_prompt
76
native_tokens_completion
6137
native_tokens_completion_images
(null)
native_tokens_reasoning
5822
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
0.00593599
router
(null)
provider_responses
0
endpoint_id
"179c6985-3a1c-48f1-a009-9f3e3e402cdd"
id
"bcca989c977b45309b4e9a198880db4b"
is_byok
false
latency
669
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-1777281268-zw0X9oRlHD1tHMhyced1"
session_id
(null)
api_type
"completions"
id
"gen-1777281268-PLijS16hHx9DwLLCfH9H"
upstream_id
"bcca989c977b45309b4e9a198880db4b"
total_cost
0.00593599
cache_discount
(null)
upstream_inference_cost
0
provider_name
"AtlasCloud"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
9.61%
Matches word count
n/a
neededClean
false
words
222
93.29%
Dialogue to Total Word Ratio
Ratio: 95.13%, Deviation: 5.13%
neededClean
false
wordsTotal
226
wordsDialogue
215
51.4515%