NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1M1X6JCJXBWVE3J418Y4SKP
Run Details
Model:
Qwen 3.8 27B (Reasoning, XHigh)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
1m 17s
Cost:
$0.014209
Provider:
Phala
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
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 crouched by the candy store, counting pastel balloons drifting past the old bakery on Maple. Bill arrived wearing a wig made of spaghetti. He smelled like burnt toast and ambition. Their target was the Gigglesworth Children's Party, where every gift would soon be unboxed by sticky hands. The plan was simple: slip in as a mime, disable the piƱata, bag the presents, and vanish before the cake arrived. Molly said, "We go at nine, Bill." Bill replied, "I bring the glue gun, okay?" Molly added, "Do not lick it. Ever." Bill whispered, "No promises, dear partner." Molly checked her tiny flashlight, which beeped like a nervous mouse. Bill balanced a box of balloons on his head. The party hall smelled of glitter and juice boxes. Through the window, a clown painted a smile on a pumpkin. Bill pointed at a shiny robot under a table. Molly nodded. She had already labeled every present in her notebook. Number one was a dragon, number two a train, number three a suspiciously expensive trumpet. They practiced walking backwards while carrying invisible treasure. Bill tripped over a trash can, but no one saw. The night waited, soft and sugary, full of stolen futures.
created_at
"2026-09-03T16:33:51.187Z"
9/3/2026, 4:33:51 PM
model
"qwen/qwen3.8-27b-20260814"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
438
moderation_latency
(null)
generation_time
76877
tokens_prompt
75
tokens_completion
3716
native_tokens_prompt
186
native_tokens_completion
4719
native_tokens_completion_images
(null)
native_tokens_reasoning
4450
native_tokens_cached
64
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"
service_tier
(null)
usage
0.014209
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788453231-GL009JQraERvfisqRyUL"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788453231-zWYw9MflWUTdg13N1179"
upstream_id
"req_0f43d58c205418a1519525f52637f964"
provider_responses
0
endpoint_id
"cfc4d0ca-df7c-4b5f-9c74-328c41a7cbc3"
id
"req_0f43d58c205418a1519525f52637f964"
is_byok
false
latency
438
model_permaslug
"qwen/qwen3.8-27b-20260814"
provider_name
"Phala"
status
200
total_cost
0.014209
cache_discount
0.0000224
upstream_inference_cost
0
provider_name
"Phala"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
100.00%
Dialogue to Total Word Ratio
Ratio: 10.00%, Deviation: 0.00%
neededClean
false
wordsTotal
200
wordsDialogue
20
100.0000%