NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1M1NYTMC0KHQQH3MC58DPM3
Run Details
Model:
Qwen 3.8 27B (Reasoning, XHigh)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
1m 48s
Cost:
$0.017814
Provider:
Parasail
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 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 taped the invitations to the van and quietly whispered, "We will steal every single present from the children's party." Bill checked the clown bouncer at the front and grinned, "He is far too busy tying a red balloon animal." Molly laughed and pulled a shiny tiny ladder from nowhere, "The piƱata is weak, so we enter through the side." Bill counted the cake, balloons, and napkins before nodding slowly, "Three gifts are hidden under the frosting, so we hurry." Molly slipped her gift bag over her shoulder and winked, "Your magic trick must distract the children for five minutes." Bill produced a squeaky rubber chicken from his party hat, "I am a magician, not a thief, but tonight counts." Molly pointed to the window covered in bright sticky confetti, "Break that glass gently, or the sprinkles will hear us." Bill knelt beside the tablecloth and carefully measured the rug, "The cake is fake, so we can steal the presents." Molly stacked boxes, ribbons, and boxes with suspicious unknown contents, "If a child asks, tell them it is a swap." Bill rolled his eyes and finally opened the van door, "Let us go before the clown learns how to juggle."
created_at
"2026-09-03T16:29:53.884Z"
9/3/2026, 4:29:53 PM
model
"qwen/qwen3.8-27b-20260814"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
227
moderation_latency
(null)
generation_time
108281
tokens_prompt
75
tokens_completion
6815
native_tokens_prompt
118
native_tokens_completion
8084
native_tokens_completion_images
(null)
native_tokens_reasoning
7825
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"
service_tier
(null)
usage
0.0178143
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788452993-F3NhqXdlojzOXPSUKZkl"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788452993-IPA4ZLrKn5SvhbAIgu8Y"
upstream_id
"chatcmpl-77865cae28654fd8c8ff78ce73403a65"
provider_responses
0
endpoint_id
"a58a4a1f-4e83-4776-a40e-9f55b72783cb"
id
"chatcmpl-77865cae28654fd8c8ff78ce73403a65"
is_byok
false
latency
227
model_permaslug
"qwen/qwen3.8-27b-20260814"
provider_name
"Parasail"
status
200
total_cost
0.0178143
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Parasail"
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: 50.00%, Deviation: 0.00%
neededClean
false
wordsTotal
200
wordsDialogue
100
100.0000%