NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-02-01M1HBK8F246SMWQNQX0PEWCJN
Run Details
Model:
Qwen 3.8 Max (Reasoning, XHigh)
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
3m 49s
Cost:
$0.057686
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 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 spread the crayon map across the van floor slowly. "We enter through the bouncy castle, grab gifts, leave quietly." Bill polished his rubber chicken disguise beside the stack nearby. "Nobody suspects a clown carrying enormous sacks of presents today." Molly adjusted her party hat and checked the guest list. "Kids are vicious, Bill, especially when pinatas are involved today." Bill packed a juice box wrench and three emergency cupcakes. "We need tools for sticky hands and sudden sugar crises." Molly circled the birthday table with a purple marker flourish. "The cake distracts them while we liberate the wrapped loot." Bill rehearsed a magical whistle that sounded like frightened ducks. "If adults arrive, I become the entertainment, you become invisible." Molly tucked a spare balloon into her belt for camouflage. "Children love balloons, criminals love balloons, everyone loves balloons, actually." Bill studied the crayon drawing of the backyard fence gate. "One squeak, and every parent becomes a detective, Molly, remember." Molly counted paper plates while calculating escape routes between chairs. "We exit after presents, not before dessert, because nobody notices." Bill wore sneakers with flashing lights for tactical confusion purposes. "These shoes annoy children, blind parents, and boost my confidence." Molly tested a small ladder against the imaginary garden wall. "I boost, you crawl, we both pretend to be magicians." Bill packed glitter as a defensive weapon and distraction too. "Glitter is the gift that keeps ruining evidence forever, Molly." Molly drew arrows pointing away from the real present pile. "Decoys are essential: empty boxes, sad ribbons, extremely boring socks." Bill practiced saying birthday wishes without giggling like a raccoon. "Happy birthday tiny citizens, please ignore the van outside now." Molly inflated a balloon until it resembled a guilty grape. "If questioned, we are party planners from another party planner." Bill placed a kazoo beside his belt for emergency authority. "Music controls mobs, especially mobs covered in frosting and rage." Molly memorized the names of imaginary friends for quick bribes. "Binky, Sparkles, Captain Noodle, nobody can resist a knowing accomplice." Bill checked the weather, then frowned at the sunny forecast. "Sunshine means barefoot children, barefoot children mean faster pursuit, Molly." Molly folded the map into a paper airplane for efficiency. "If we panic, throw confetti, smile widely, and run backwards." Bill attached tiny bells to his gloves to detect movement. "Every jingle tells me where small enemies are gathering now." Molly painted a fake mustache on a balloon for realism. "Adults trust mustaches, children fear mustaches, both ignore mustaches sometimes." Bill packed bandages, lollipops, and one suspiciously squeaky rubber duck. "Injuries happen when presents become heavier than moral responsibility apparently." Molly rehearsed an innocent whistle while holding a giant sack. "We are not thieves, we are aggressive gift movers today." Bill taped a sign to the van reading professional entertainment. "If they read it, they believe it, usually, probably, hopefully." Molly opened the van doors toward the distant laughing children. "Remember, Bill, we steal presents, not joy, except maybe cake."
created_at
"2026-09-02T15:25:27.915Z"
9/2/2026, 3:25:27 PM
model
"qwen/qwen3.8-max-20260803"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1112
moderation_latency
(null)
generation_time
228479
tokens_prompt
75
tokens_completion
9655
native_tokens_prompt
127
native_tokens_completion
9572
native_tokens_completion_images
(null)
native_tokens_reasoning
8869
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
0.057686
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788362727-IaSHCAOROSLlvJIO5cO3"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788362727-lPllrlnECbMIx29zsXWv"
upstream_id
"chatcmpl-3c05ff2d-7f3a-98e9-8a86-297edcb65c20"
provider_responses
0
endpoint_id
"6332e9fd-e0c4-4cae-8c17-d25bc774864a"
id
"chatcmpl-3c05ff2d-7f3a-98e9-8a86-297edcb65c20"
is_byok
false
latency
1112
model_permaslug
"qwen/qwen3.8-max-20260803"
provider_name
"Alibaba"
status
200
total_cost
0.057686
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: 50.00%, Deviation: 0.00%
neededClean
false
wordsTotal
500
wordsDialogue
250
100.0000%