NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-02-01M1HAXB9P0V7ZRKKRRN5G5TEX
Run Details
Model:
Qwen 3.8 Max (Reasoning, XHigh)
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
4m 56s
Cost:
$0.086456
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 flattened herself beside the fence while Bill held cupcakes. “Molly, the bouncy castle is definitely watching me right now.” “It is not watching you, Bill. It has painted eyes.” “Painted eyes are worse, Molly. They see every criminal choice.” “Focus. The presents are under the cake table right now.” “All of them? Even the suspiciously lumpy little blue ones?” “Especially those. Lumpy presents are either expensive toys or socks.” “We steal socks too? I thought we always had standards.” “Standards are optional. Tonight we steal every present in sight.” “Professional. Silent. I am practically invisible when I am sneaking.” “You chewed a candy whistle during our serious planning meeting.” Bill crept toward the garden gate and pointed at children. “Molly, there are children. Many children. Twenty children, maybe more.” “Twenty is a swarm, but they are distracted by magic.” “A clown? Is the clown committed to his silly work?” “Very committed. If he turns, we turn much faster away.” “Plan again. I need comfort before we commit terrible theft.” “We enter quietly, grab the sack, swap it, leave fast.” “What is in the decoy sack you brought along today?” “My old toys. Sentimental, but perfect camouflage for small crimes.” “What if a child wants a present from our sack?” “You hiss. Hissing terrifies children and interrupts polite birthday conversation.” “I cannot hiss. I have a very gentle criminal throat.” “Then cough menacingly. Menacing coughs are your only real talent.” “Molly, what if that clown recognizes us from last year?” “We robbed a different circus. Eyebrows are not solid evidence.” Bill lifted a paper plate with two holes punched out. “This is a plate, not a proper criminal mask, Molly.” “It is a mask. Cake makes excellent disguise material too.” “Cake is evidence. Eat the evidence before anyone notices us.” He ate part of the mask and smiled very proudly. “Now it is a crescent moon. Extremely mysterious and stylish.” “Molly, I hear music. Children are starting to dance wildly.” “It is freeze dance. We move when they freeze still.” “Like ninjas. Festive ninjas carrying enormous sacks of stolen presents.” “Quiet. This is our moment. Do not step on children.” “Do not step on presents. Do not apologize either, Bill.” “I always apologize. It is my nicest criminal habit, Molly.” “Tonight you are a shadow. Shadows never apologize for anything.” The clown spun a balloon giraffe while children screamed happily. Molly grabbed Bill by his collar and pushed him forward. The gate squeaked, but butter made it almost silent again. They slipped into the yard as bubbles filled the air. The sack under the cake table looked enormous and lumpy. Bill pocketed a frosting star and burped softly with pride. They lifted the sack, swapped it, then froze instantly nearby. A tiny child stared at them with serious birthday suspicion. Molly shook her head while Bill whispered absolutely nothing useful. They marched out slowly, carrying every present and one star. Somewhere behind them, the clown began another extremely silly song.
created_at
"2026-09-02T15:13:29.923Z"
9/2/2026, 3:13:29 PM
model
"qwen/qwen3.8-max-20260803"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1143
moderation_latency
(null)
generation_time
295870
tokens_prompt
75
tokens_completion
12037
native_tokens_prompt
127
native_tokens_completion
14367
native_tokens_completion_images
(null)
native_tokens_reasoning
13656
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
0.086456
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788362009-Uw0Nf5Q9NRaDoVzjSLqV"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788362009-3FK9OfV9t1tIbP8MthUJ"
upstream_id
"chatcmpl-667fc8a8-3e2b-98c9-9a17-0c6031ac3378"
provider_responses
0
endpoint_id
"6332e9fd-e0c4-4cae-8c17-d25bc774864a"
id
"chatcmpl-667fc8a8-3e2b-98c9-9a17-0c6031ac3378"
is_byok
false
latency
1143
model_permaslug
"qwen/qwen3.8-max-20260803"
provider_name
"Alibaba"
status
200
total_cost
0.086456
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%