NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-02-01M1HCWD1TSRT4B9J90VB4YHKA
Run Details
Model:
Qwen 3.8 Max (Reasoning, XHigh)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
3m 57s
Cost:
$0.060386
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 spread the napkin map. "The piñata is a distraction." Bill adjusted his tiny clown nose. "From the cake?" Molly checked the party schedule. "From the presents, Bill." Bill winked twice, poorly. "Right. Presents. Shiny, numerous, unguarded presents." "By clowns?" "Especially clowns. Clowns notice nothing but their own shoes." "So we enter as entertainment?" "Exactly. You juggle." "I can't juggle." "You can panic while holding oranges. Children love that." "And you?" "I am the magician." "What trick?" "The Vanishing Gifts." "Subtle." "Children are drunk on juice." "What about the birthday boy?" "Point at the cake, he will follow." "What about the parents?" "Parents are furniture with wine." "What about the good balloons?" "We take them too." "But balloons are loud." "So is crime." "Crime squeaks?" "Crime squeaks." "And the piñata?" "The piñata is our alibi." "An alibi with candy?" "The best kind." "This plan is ridiculous." "Profitable." "Fair. Entrance at two?" "Two fifteen, during balloon animals." "Exit?" "Through the puppet stage." "With what?" "Every present." "All of them?" "Every sock, doll, and suspiciously lumpy train set." "They'll cry." "They'll blame the clowns." "The clowns will cry." "Professional hazard. Now smile, Bill. We're bringing joy." "By stealing everything?" "By liberating it."
created_at
"2026-09-02T15:47:56.098Z"
9/2/2026, 3:47:56 PM
model
"qwen/qwen3.8-max-20260803"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1475
moderation_latency
(null)
generation_time
236489
tokens_prompt
75
tokens_completion
8139
native_tokens_prompt
127
native_tokens_completion
10022
native_tokens_completion_images
(null)
native_tokens_reasoning
9649
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
0.060386
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788364076-Z9Nni6tpynPEss4lgl5r"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788364076-9qelQIgkvFoeIoIU35E8"
upstream_id
"chatcmpl-1978b9e3-fdb6-9035-9113-d8040b5f7749"
provider_responses
0
endpoint_id
"6332e9fd-e0c4-4cae-8c17-d25bc774864a"
id
"chatcmpl-1978b9e3-fdb6-9035-9113-d8040b5f7749"
is_byok
false
latency
1475
model_permaslug
"qwen/qwen3.8-max-20260803"
provider_name
"Alibaba"
status
200
total_cost
0.060386
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%