NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ73Y2Q9RQRFBC056VM2WEHE
Run Details
Model:
Qwen 3.6 35B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
30.9s
Cost:
$0.003812
Provider:
AtlasCloud
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
95.69%
Dialogue to Total Word Ratio
(details)
97.8048%
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
"Okay, Bill, listen up," Molly hissed adjusting her tiara. "The target is the living room tree. We move at the cake cutting. That's when the parents are vulnerable, distracted by sugar crashes and 'Happy Birthday' chants." "Got it," Bill whispered, checking his fake mustache. "I'll create a distraction." "Don't use the inflatable dinosaur again. It scares the kids too much." "Fine, I'll just juggle the glow sticks until someone cries." "Perfect. While Bill causes a ruckus, I'll sweep the gift pile into the sack. Remember, no opening the loot until we're three towns over. The wrapping paper makes a lot of noise." "What if the dog sees us?" "The dog is with me. I have three premium biscuits in my garter." "And the parents?" "They won't know what hit them. By the time they check the tree, we'll be gone, leaving behind only a single, unblown balloon and a profound sense of confusion." "I love the confusion." "Focus, Bill. We're in this for the big stuff. The Nintendo Switches, the Lego castles, the premium chocolate coins." "What about the socks?" "Leave the socks. We have standards, Bill." "Right. Socks are for amateurs." "Bill, did you pack the burlap sacks?" "In the pocket. Shh."
created_at
"2026-04-27T09:22:11.313Z"
4/27/2026, 9:22:11 AM
model
"qwen/qwen3.6-35b-a3b-20260415"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1916
moderation_latency
(null)
generation_time
30839
tokens_prompt
77
tokens_completion
3658
native_tokens_prompt
76
native_tokens_completion
3937
native_tokens_completion_images
(null)
native_tokens_reasoning
3630
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
0.00381244
router
(null)
provider_responses
0
endpoint_id
"179c6985-3a1c-48f1-a009-9f3e3e402cdd"
id
"e3d547c906c04514888fa11aab059f92"
is_byok
false
latency
1916
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-1777281731-NxUU83jaJggmz4B3H6JH"
session_id
(null)
api_type
"completions"
id
"gen-1777281731-9g7LMucR3Mp27C7IazbL"
upstream_id
"e3d547c906c04514888fa11aab059f92"
total_cost
0.00381244
cache_discount
(null)
upstream_inference_cost
0
provider_name
"AtlasCloud"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.92%
Matches word count
n/a
neededClean
false
words
203
95.69%
Dialogue to Total Word Ratio
Ratio: 94.58%, Deviation: 4.58%
neededClean
false
wordsTotal
203
wordsDialogue
192
97.8048%