NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ72PBF23PDD1W0ADRA3VHA1
Run Details
Model:
Qwen 3.6 35B
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
1m 13s
Cost:
$0.011330
Provider:
AtlasCloud
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.99%
Dialogue to Total Word Ratio
(details)
99.9950%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 utility belt, checking the tension on the burlap sacks. Bill paced the sidewalk, eyeing the brightly colored bunting draped over the fence. He checked his watch before the party began. "The piƱata guards are predictable," Molly whispered. "They follow the rhythm of the music." Bill lowered his notes. He stared. "Predictable does not mean harmless. Inflatable dinosaurs trip us constantly." She checked her watch. She blinked. "Outmaneuver them. The presents go under the tree at exactly eight fifteen." Bill exhaled slowly, visualizing the route across the lawn. "Eight fifteen is tight. Negotiating with a toddler takes forever." Molly stepped closer to the iron gate. "The toddler gets a thank you card. Simple arithmetic works." Bill folded his clipboard. "Arithmetic assumes the mother forgets the glow sticks." She smiled and tested the weight of the empty sacks. "Glow sticks illuminate the targets. Check the capacity carefully." Bill nodded, watching the first balloons rise into the twilight sky. "They will hold twelve gift bags. Perfect. Move at eight sharp." Molly kicked the grass flat and prepared to climb the fence. "Trust the timing, not the toys." "Grab the heavy bags first. We leave no evidence behind." The heist began.
created_at
"2026-04-27T09:00:29.544Z"
4/27/2026, 9:00:29 AM
model
"qwen/qwen3.6-35b-a3b-20260415"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1026
moderation_latency
(null)
generation_time
72703
tokens_prompt
77
tokens_completion
10123
native_tokens_prompt
76
native_tokens_completion
11725
native_tokens_completion_images
(null)
native_tokens_reasoning
11434
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
0.011329807
router
(null)
provider_responses
0
endpoint_id
"179c6985-3a1c-48f1-a009-9f3e3e402cdd"
id
"09b3f6ee040846fb9b97bfcc32de5bd3"
is_byok
false
latency
1026
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-1777280429-cqO15i2O7h04nz2C7WOf"
session_id
(null)
api_type
"completions"
id
"gen-1777280429-CqCdJOhsctv7Yfsi4nta"
upstream_id
"09b3f6ee040846fb9b97bfcc32de5bd3"
total_cost
0.011329807
cache_discount
(null)
upstream_inference_cost
0
provider_name
"AtlasCloud"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
99.99%
Dialogue to Total Word Ratio
Ratio: 49.00%, Deviation: 1.00%
neededClean
false
wordsTotal
200
wordsDialogue
98
99.9950%