NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-02-01M1HCVFFT80M9Q7WNPY1JJ3SC
Run Details
Model:
Qwen 3.8 Max (Reasoning, XHigh)
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
7m 26s
Cost:
$0.130106
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 a crayon map across the sticky van floor. "The target is a birthday party on Maple Drive today." Bill adjusted a fake mustache and consulted a stained list. "Forty presents, one chocolate fountain, and a suspicious clown outside." Molly tapped the bouncy castle with a purple crayon tip. "Clowns notice everything, especially thieves carrying oversized gift bags inside." Bill snapped his fingers and immediately regretted that loud decision. "Then we bring a large piñata instead of obvious bags." She said it with the calm of a true genius. "Nobody questions a piñata at a loud children's party ever." He tapped the colorful paper shell with one doubtful finger. "What exactly is inside this festive paper horse right now?" Molly smiled like a villain wearing a very small hat. "Empty space, ambition, and a few emergency candy wrappers too." Bill had once engineered cardboard castles for serious toddlers everywhere. "That is structurally unsound and deeply confusing for young children." She closed the map with dramatic dignity and one crumb. "It is morally sound, which matters more than physics here." Bill checked a watch shaped like a green dinosaur face. "The party starts at two, cake at three, presents after." She drew arrows around a rabbit wearing a trench coat. "We enter during the magic trick and collect every present." He straightened a bow tie that was already perfectly crooked. "I will be the entertainment assistant with extraordinary juggling skills." She held up a balloon animal resembling a disappointed sausage. "I will be the lost balloon artist seeking the party." His mustache twitched with unexpected conscience and orange frosting residue. "What if the birthday boy cries about missing his presents?" She produced an envelope sparkling like a tiny crime scene. "We leave him a glitter card and two shiny stickers." He had seen the message, which featured aggressive sparkling handwriting. "That card is insulting, even for professional birthday thieves too." That explained everything and nothing, like most criminal plans do. "It has glitter, so legally it counts as apology now." He lowered his voice as if cupcakes could inform them. "What about the parents and their suspicious grilling habits anyway?" Molly listed adults like enemy positions on a birthday battlefield. "One mother organizes hats, another films, father guards the grill." A single bead of sweat appeared suddenly on his forehead. "The clown remains a serious threat to our entire operation." She sounded extremely certain while holding a stolen rubber chicken. "We flatter him, because clowns survive on applause and compliments." He lifted the piñata with two fingers and immediate suspicion. "This festive horse weighs nothing, which feels criminal to me." She patted the piñata gently like a sleeping paper crocodile. "It will weigh more when full of stolen birthday presents." He practiced an innocent expression, which made him look guilty. "If someone asks questions, what do we say to them?" She placed the balloon sausage gently in his trembling hands. "You say we are creating a memory for everyone here."
created_at
"2026-09-02T15:47:25.827Z"
9/2/2026, 3:47:25 PM
model
"qwen/qwen3.8-max-20260803"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1404
moderation_latency
(null)
generation_time
446172
tokens_prompt
75
tokens_completion
18463
native_tokens_prompt
127
native_tokens_completion
21642
native_tokens_completion_images
(null)
native_tokens_reasoning
20982
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
0.130106
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788364045-9Fkco5JL9Wzu6vXe2Njw"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788364045-87FPpcbrX5wsF77OET6V"
upstream_id
"chatcmpl-633a6695-6c14-9b63-8a7b-bda25555b465"
provider_responses
0
endpoint_id
"6332e9fd-e0c4-4cae-8c17-d25bc774864a"
id
"chatcmpl-633a6695-6c14-9b63-8a7b-bda25555b465"
is_byok
false
latency
1399
model_permaslug
"qwen/qwen3.8-max-20260803"
provider_name
"Alibaba"
status
200
total_cost
0.130106
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%