NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-02-01M1HHVSZA40G4FRYM3X1H6RWM
Run Details
Model:
Qwen 3.8 Flash (Reasoning)
Test:
Dialogue tags
Scenario:
Write 500 words with 30% dialogue
Duration:
6m 43s
Cost:
$0.018008
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.98%
Dialogue to Total Word Ratio
(details)
99.9910%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 30% 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 pressed her ear to the vinyl siding of the Henderson house, listening for shrieks of birthday children. Bill crouched beside her with a burlap sack and the confidence of a raccoon wearing a tie. The backyard glittered through a gap in the hedge: streamers, a papier-mâché dragon, and a table stacked with wrapped boxes. A woman in a unicorn T-shirt inflated a soccer ball while three children debated whether dinosaurs had eyelashes. “You want the blue box?” Molly whispered. Bill looked at her. “No.” “That was my question.” “Your question is not my answer.” “You are insufferable.” “I am prepared.” Bill pulled a tiny map. He had drawn it in crayon, because Molly had warned him not to bring real plans. Real plans had fingerprints, he had argued, and fingerprints had feelings. “We hit after the piñata,” Molly said. “Grief, glitter, juice boxes.” “Beautiful,” Bill said. “Like a crime.” “Where is the table?” “Under the table.” “Useful.” “It is.” A small boy pointed at the bushes and yelled that someone was there. Molly shoved Bill into the hydrangeas. They lay flat among petals and panic while the woman came outside, peering at them like a confused fairy. “Are you the clown?” Molly whispered. “I am,” Bill squeaked. “Good. Balloon trick first.” Molly felt the earth try to swallow her. The woman returned inside. Bill adjusted his beanie. “Why are you a clown?” Molly asked. “It felt true.” “Everything you touch is embarrassing.” “The children are laughing.” “Exactly why we leave.” The piñata exploded. Children roared. Confetti shot into twilight like paper bullets. Through the chaos, Molly and Bill slithered across the yard and reached the table. A talking doll rested on top, its plastic eyes fixed on destiny. Molly opened the sack. Bill swept presents into it with the practiced speed of a man who had stolen an entire bakery. The birthday boy turned, saw the sack, and considered screaming, then considered biting, then chose screaming because he had been raised properly. “Hey!” Bill shouted. “Those are mine!” “Temporary property,” Molly said. “They’re toys!” “They’re evidence.” “Did you get the remote car?” Bill whispered. “Yes.” “The dangerous one?” “The dangerous one.” Bill zipped the sack. “Left?” “Left.” They bolted across the lawn, scattering cake crumbs and a plastic dinosaur. Behind them, the birthday boy screamed with the fury of a child deprived of gifts but impressed by their exit. Molly counted boxes under a streetlight. “Fourteen.” Bill pouted. “Small party.” “Meticulous planning,” Molly said. “We fence receipts tomorrow.” Bill frowned. “We fence receipts?” The sack shifted. Inside, the doll whined. Bill said, “Nope,” dropping it. Molly caught it, shoved it back, and pulled the drawstring shut. “We have a talking doll,” Bill said. “A talking doll is a problem.” “A talking doll is profit.” “You can’t fence a child’s toy.” “I fence anything.” “It’s a curse.” “It’s inventory.” “Inventory talks.” “That’s normal.” They vanished into the night, carrying joy, wrapping paper, and one hungry doll. “I’m tired,” Molly said.
created_at
"2026-09-02T17:16:18.75Z"
9/2/2026, 5:16:18 PM
model
"qwen/qwen3.8-flash-20260826"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
788
moderation_latency
(null)
generation_time
323805
tokens_prompt
75
tokens_completion
29129
native_tokens_prompt
127
native_tokens_completion
38274
native_tokens_completion_images
(null)
native_tokens_reasoning
37520
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
0.01800783
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788369378-8A7wNASSMLfh9GgVuzLz"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788369378-edqA8KgqCaXCdtrMG40c"
upstream_id
"chatcmpl-9f44b789-a27b-9238-bb1f-d9e3bf333201"
provider_responses
0
endpoint_id
"84b1e4a7-5aed-4464-818f-1994f0b4ee18"
id
"chatcmpl-9f44b789-a27b-9238-bb1f-d9e3bf333201"
is_byok
false
latency
788
model_permaslug
"qwen/qwen3.8-flash-20260826"
provider_name
"Alibaba"
status
200
total_cost
0.01800783
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
99.98%
Dialogue to Total Word Ratio
Ratio: 29.94%, Deviation: 0.06%
neededClean
false
wordsTotal
501
wordsDialogue
150
99.9910%