NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ72JZGT962PEGCY2FG4AS76
Run Details
Model:
Qwen 3.6 35B
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
47.4s
Cost:
$0.009735
Provider:
Parasail
Evaluation summary
Score
Evaluator
Details Link
43.38%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
40.0831%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 stained leotard, peering through the fence at the bouncy castle's jet-engine hum. Target Sector Four: the living room carpet, a glittering hoard of boxes labeled 'For Timmy' nestled among crushed crackers. Bill fumbled with a jam jar marked 'Goo,' mistaking it for thermal paste, while gnawing a plastic spoon. The security detail included a snoring golden retriever and a mother napping on the sofa with the intensity of a sleep-deprived dragon. "Check the perimeter," Molly hissed. Bill nodded frantically, dropping the spoon with a gong-like clatter. "Got the goo, boss," he squeaked, wiping crimson slime onto his knee pads. The dog twitched but remained comatose. Molly grabbed Bill's ankle as the mother stirred, eyes fluttering open as a waking zombie before drifting shut again. "Watch the spoon," Molly warned, pointing to the jagged utensil protruding from Bill's grip. "I'm watching, I swear," Bill lied, sweating profusely. "Just grab the robot and run," she commanded, eyes locked on the robot prize awaiting rescue. They moved with the grace of intoxicated flamingos, creeping past a squeaky balloon arch toward the loot pile.
created_at
"2026-04-27T08:58:39.011Z"
4/27/2026, 8:58:39 AM
model
"qwen/qwen3.6-35b-a3b-20260415"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
359
moderation_latency
(null)
generation_time
37159
tokens_prompt
77
tokens_completion
4726
native_tokens_prompt
76
native_tokens_completion
4854
native_tokens_completion_images
(null)
native_tokens_reasoning
4430
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
0.0097346
router
(null)
provider_responses
0
endpoint_id
"179c6985-3a1c-48f1-a009-9f3e3e402cdd"
is_byok
false
latency
10077
model_permaslug
"qwen/qwen3.6-35b-a3b-20260415"
provider_name
"AtlasCloud"
status
504
1
endpoint_id
"57ebdffc-b059-4d92-a1ac-94436bae3d31"
id
"chatcmpl-91251609fc5056b7"
is_byok
false
latency
359
model_permaslug
"qwen/qwen3.6-35b-a3b-20260415"
provider_name
"Parasail"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777280319-4aj598unjaWBtedTRRer"
session_id
(null)
api_type
"completions"
id
"gen-1777280319-jrkB204CI4RYUF06DhPu"
upstream_id
"chatcmpl-91251609fc5056b7"
total_cost
0.0097346
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Parasail"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
43.38%
Matches word count
n/a
neededClean
false
words
183
36.79%
Dialogue to Total Word Ratio
Ratio: 20.00%, Deviation: 10.00%
neededClean
false
wordsTotal
185
wordsDialogue
37
40.0831%