NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-02-01M1H9XDDYV37CN1FY2YE8NY7Y
Run Details
Model:
Qwen 3.8 Max (Reasoning, XHigh)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
2m 24s
Cost:
$0.042338
Provider:
Alibaba
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 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
Molly tapped the map. "The bouncy castle guards the gift table." Bill grinned. "So we arrive as magicians." "Magicians carry large suspicious boxes." "Exactly. Perfect." "Who hires magicians?" "The parents do. We bring cupcakes too." "Cupcakes make us generous criminals." "Generous criminals blend in." "And the piñata?" "We avoid the piñata. It has opinions." "It is a donkey, Bill." "A judgmental donkey." "Focus. We enter, smile, grab presents, exit." "What if a child wants a balloon animal?" "You make one." "I only know snakes." "Make snakes. Children love snakes." "Not at parties." "Then make a shorter snake." Molly sighed. "Plan summary: magician, cupcakes, snakes, presents." Bill raised a gloved hand. "And dignity." "We lost dignity last heist." "We rented it back." "Fine. At three." "What about the cake?" "We leave the cake. Cake is evidence." "Evidence of what?" "Fun. We are professionals." "Professionals still eat cake." "Not on the job." "The job involves cupcakes." "That is catering. Different paperwork." "And if balloons block the doorway?" "We pop them quietly." "With apology notes." "Notes slow the escape." "Then very small notes." "Fine. Three o'clock, sharp." Molly carefully checked the stolen party invitations. "We absolutely never discuss the clown. Ever. Understood, Bill?"
created_at
"2026-09-02T14:56:03.527Z"
9/2/2026, 2:56:03 PM
model
"qwen/qwen3.8-max-20260803"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2539
moderation_latency
(null)
generation_time
143499
tokens_prompt
75
tokens_completion
5258
native_tokens_prompt
127
native_tokens_completion
7014
native_tokens_completion_images
(null)
native_tokens_reasoning
6665
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
0.042338
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788360963-v9sDpM3wMWxvwUj61Sbj"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788360963-rzANqX9CFSTa9GjO6h0c"
upstream_id
"chatcmpl-6c6b0ee7-f8db-9ee5-bcc8-ef334c21a6a4"
provider_responses
0
endpoint_id
"6332e9fd-e0c4-4cae-8c17-d25bc774864a"
id
"chatcmpl-6c6b0ee7-f8db-9ee5-bcc8-ef334c21a6a4"
is_byok
false
latency
2539
model_permaslug
"qwen/qwen3.8-max-20260803"
provider_name
"Alibaba"
status
200
total_cost
0.042338
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
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: 90.00%, Deviation: 0.00%
neededClean
false
wordsTotal
200
wordsDialogue
180
100.0000%