NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-02-01M1HAN2PERBKXCWNY06BVAAJD
Run Details
Model:
Qwen 3.8 Max (Reasoning, XHigh)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
1m 43s
Cost:
$0.030410
Provider:
Alibaba
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 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 unfolded the crayon map of the birthday venue, which was suspiciously similar to a pizza menu. The target: little Poppy’s garden party. The objective: every wrapped present, including the suspiciously light one labeled "Emergency Socks." Molly said, "The bouncy castle is our Trojan horse." Bill adjusted his tiny fake mustache and checked the schedule: cake, games, mandatory crying. He had prepared disguises as entertainers, though his balloon animal looked like a legal dispute. Bill replied, "I hate clowns." Molly reminded him they were not clowns, merely magicians with exceptional greed and a ladder. She marked the route: enter through the puppet theatre, bypass the juice boxes, avoid the goat, and extract gifts during Musical Statues. Molly whispered, "Grab the piñata." Bill nodded solemnly. "Bring extra bags." The piñata contained candy, but also possibly evidence, or more candy. Molly tucked glitter into her utility belt for emergencies, distractions, and dramatic effect. Bill pocketed a whistle he would absolutely blow by accident. Molly asked, "For glitter?" Bill said, "Obviously." Molly grinned. "Right." They toasted with empty juice boxes, then practiced looking innocent. It was terrifying. Somewhere beyond the fence, a child screamed about sharing, and both criminals shuddered in professional disgust.
created_at
"2026-09-02T15:08:58.968Z"
9/2/2026, 3:08:58 PM
model
"qwen/qwen3.8-max-20260803"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
881
moderation_latency
(null)
generation_time
103326
tokens_prompt
75
tokens_completion
4105
native_tokens_prompt
127
native_tokens_completion
5026
native_tokens_completion_images
(null)
native_tokens_reasoning
4744
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
0.03041
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788361738-ahqOrUOxOYLgvTaqqAgZ"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788361738-a9BQEPAscrn4vrofdnd5"
upstream_id
"chatcmpl-2b89bc3c-4511-9f6f-b7d1-f76e07769af0"
provider_responses
0
endpoint_id
"6332e9fd-e0c4-4cae-8c17-d25bc774864a"
id
"chatcmpl-2b89bc3c-4511-9f6f-b7d1-f76e07769af0"
is_byok
false
latency
881
model_permaslug
"qwen/qwen3.8-max-20260803"
provider_name
"Alibaba"
status
200
total_cost
0.03041
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
99.99%
Dialogue to Total Word Ratio
Ratio: 11.00%, Deviation: 1.00%
neededClean
false
wordsTotal
200
wordsDialogue
22
99.9950%