NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-02-01M1HB19S8VWEEQFV1CFT0T7N9
Run Details
Model:
Qwen 3.8 Max (Reasoning, XHigh)
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
5m 28s
Cost:
$0.088796
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 500 word scene that has 70% 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 crayon map across the rainy kitchen table. "The party starts at two with cake and silly clowns." Bill polished a tiny grappling hook with his lucky sock. "Clowns are witnesses. We need cupcakes as tasty distraction snacks." Molly tapped the bouncy castle drawn in purple crayon twice. "We enter through the castle, disguised as exhausted angry parents." Bill nodded, wearing a paper hat found under the sofa. "Parents bring presents. We bring a wagon and fake smiles." Molly counted candy buttons into a jar marked emergency bribes. "Every child gets a balloon. Every balloon hides a present." Bill drew a mustache on the party invitation with mustard. "Mustard says we belong. Mustard says we are daring professionals." Molly unfolded a blueprint covered in frosting and glitter stickers. "The gift table sits beside the pinata, guarded by grandparents." Bill gasped and dropped his grappling hook into hot tea. "Grandpas have eyes. Grandmas have radar. Children have sticky hands." Molly pinned a balloon sketch above the warm kitchen stove. "I will juggle. You will sulk. Kids love sulking jugglers." Bill practiced sulking while holding wooden spoon like royal scepter. "If a child cries, offer crackers. If parents cry, run." Molly checked her watch, which played a lullaby very incorrectly. "At three, magic show. At four, presents disappear very politely." Bill packed a duffel bag with clown shoes and rope. "Shoes are for escape. Rope is for the pinata emergency." Molly attached a fake mustache to a squeaky toy microphone. "Announce nap time. No small child resists nap time quietly." Bill shuddered, remembering a toddler with frosting on both eyebrows. "Toddlers are tiny security guards with no fear at all." Molly poured juice into two bottles labeled courage for tonight. "Drink courage. Spit out juice. Do not lick shiny wrappers." "We borrow a mascot costume. A fluffy rabbit inspires trust." "If the rabbit itches, maintain mystery. Children respect noble mystery." "Bring stickers for good behavior and extra stickers for bribery." "Bribery sounds criminal. Call it generous community gift redistribution work." "The magician will need volunteers. We volunteer the presents first." "Ask politely. Wave receipt. No receipt? Invent one very confidently." "Receipts are for returns. We are collecting precious childhood memories." "Memories weigh nothing. Presents weigh plenty. Bring reinforced red wagon." "If asked, we are auditors checking present safety standards today." "Auditors wear badges. Make badges from cereal boxes right away." "Glue sticks are evidence. So are sprinkles. Avoid all sprinkles." "Sprinkles betray thieves. They enter shoes and tell long stories." "After cake, faces become sticky. Sticky faces identify fleeing suspects." "We wear bibs. We say we are catering trainees here." "Trainees carry trays. Trays carry presents. Nobody questions shiny trays." "If balloons attack, stay calm. Balloons fear sharp adult confidence." "Adults are suspicious. Become mysterious entertainer with three rubber chickens." "Chickens squeak. Squeaking signals distress. Distress attracts anxious mothers quickly." "Mothers notice everything. Compliment decorations. Ask about bathroom location politely." "Then vanish with presents before anyone notices missing wrapping paper."
created_at
"2026-09-02T15:15:39.441Z"
9/2/2026, 3:15:39 PM
model
"qwen/qwen3.8-max-20260803"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1354
moderation_latency
(null)
generation_time
327949
tokens_prompt
75
tokens_completion
13996
native_tokens_prompt
127
native_tokens_completion
14757
native_tokens_completion_images
(null)
native_tokens_reasoning
14014
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
0.088796
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788362139-HQAtoWUHIUd9Ofx63BsT"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788362139-LWNfoABw3osKOy8GhdkU"
upstream_id
"chatcmpl-d47e594f-227f-9b90-97ce-90b7a8b21e55"
provider_responses
0
endpoint_id
"6332e9fd-e0c4-4cae-8c17-d25bc774864a"
id
"chatcmpl-d47e594f-227f-9b90-97ce-90b7a8b21e55"
is_byok
false
latency
1354
model_permaslug
"qwen/qwen3.8-max-20260803"
provider_name
"Alibaba"
status
200
total_cost
0.088796
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
500
100.00%
Dialogue to Total Word Ratio
Ratio: 70.00%, Deviation: 0.00%
neededClean
false
wordsTotal
500
wordsDialogue
350
100.0000%