NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-02-01M1H9HEAJQDRDX4A1RZS74H6T
Run Details
Model:
Qwen 3.8 Max (Reasoning, XHigh)
Test:
Dialogue tags
Scenario:
Write 500 words with 30% dialogue
Duration:
6m 57s
Cost:
$0.125906
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 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 spread the stolen invitation across the dashboard. It said Bring Your Own Magic, which she considered a security failure. Bill was already trying on a paper hat he had found in a nearby bin. The party began at noon. "The presents will be under the cake table," Molly said. Bill folded the hat into a smaller, sadder hat. "Which cake table? There are six." "The one shaped like a pirate ship," Molly said. Bill checked his pocket for tools and found a juice coupon. "That is near the screaming." Molly had planned the job for three weeks, mostly because the house belonged to a woman named Sandra, who owned a label maker and used it like a weapon. Even the garden gnome looked unionised. Bill had suggested burning it down, but Molly preferred crime that left minimal paperwork. "We enter as entertainers," Molly said. "I am not entertaining." "You are wearing a bin hat." "It gives me authority." "It gives me worry." Molly unrolled a crayon map of the garden. The bouncy castle blocked the kitchen gate. The presents were piled beside a painted paper parrot, which Bill insisted was a witness. He wanted to kidnap it. Molly refused because witnesses were heavy and would judge them later in silence for months. "We need a distraction," Molly said. "I can juggle." "With what?" "Socks." "Whose socks?" "The kids." "Bill, no." "Bill, yes." "Fine, steal the socks first." "That is always the plan." At three sharp, they parked beside a hedge shaped like a disappointed whale. Inside the garden, children ran in circles, armed with paper swords and the terrifying certainty of people who had recently eaten sugar. A clown was already present, but he looked unemployed and possibly haunted by his own shoes. Molly watched the clown. "If he cries, we move." Bill inflated a balloon. "If he cries loudly?" "Then we move faster." "I like crying." "Not professionally." "I cry professionally." "You cried at a robbery." "It was a beautiful robbery." Sandra emerged carrying a tray of cupcakes, each decorated with a face that demanded legal representation. The children stopped screaming for exactly one second, which Molly recognised as the only opportunity available. She signalled to Bill. He responded by dropping the balloon and stepping on it like a man killing a small ghost. The piƱata rose above the fence, a painted paper donkey with one ear and a criminal expression. Bill stared at it. Molly stared at the presents. The children stared at the snacks, proving that greed was universal and age was merely a suggestion. Molly whispered, "Grab the sacks. Ignore the donkey. Compliment the napkins if necessary. Do not mention the goat." Bill whispered, "What about the goat?" "We do not have a goat." "I brought one." "Why?" "For extraction. And emotional support." "You are impossible." "That is my job." "Exactly." Sandra turned. The children screamed. The heist began with glitter, goat panic, and a coupon nobody intended to honour for anything at all today.
created_at
"2026-09-02T14:49:31.228Z"
9/2/2026, 2:49:31 PM
model
"qwen/qwen3.8-max-20260803"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1091
moderation_latency
(null)
generation_time
417330
tokens_prompt
75
tokens_completion
16905
native_tokens_prompt
127
native_tokens_completion
20942
native_tokens_completion_images
(null)
native_tokens_reasoning
20262
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
0.125906
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788360571-7UrCzQ8jUnXKKVlfeuc1"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788360571-9XcYLZ4X1bp9U94EKrdm"
upstream_id
"chatcmpl-b73bb627-2576-9ec3-afc9-dd33de2ac537"
provider_responses
0
endpoint_id
"6332e9fd-e0c4-4cae-8c17-d25bc774864a"
id
"chatcmpl-b73bb627-2576-9ec3-afc9-dd33de2ac537"
is_byok
false
latency
1091
model_permaslug
"qwen/qwen3.8-max-20260803"
provider_name
"Alibaba"
status
200
total_cost
0.125906
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: 30.00%, Deviation: 0.00%
neededClean
false
wordsTotal
500
wordsDialogue
150
100.0000%