NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ788JH1BQXWHWCHYRQ0ERPM
Run Details
Model:
Qwen3.6 Max Preview
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
3m 7s
Cost:
$0.054512
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 200 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 unfolded the crayon blueprint across the sticky diner table. Bill adjusted his black ski mask, ignoring the confused waitress pouring coffee. He tapped a grease stain marking the inflatable castle. The lights hummed overhead, casting long shadows across the menu. "We strike during the puppet show. The felt dragon provides perfect visual cover. You grab the stacked boxes near the gift table. I will neutralize the piƱata guard with tactical juice boxes." Bill sighed, stirring three sugar packets into his mug. He studied the crude map, noting the escape route past the petting zoo. A siren wailed, reminding them time was slipping. "Are we really risking prison for plastic trains and stuffed giraffes? These parents buy organic wooden blocks. We fence them to desperate grandparents by Tuesday. Fine, but I refuse to wear squeaky clown shoes again." Molly rolled her eyes, sliding a duffel bag under the booth. She checked her watch, counting down the minutes until chaos. Rain tapped glass, matching his nervous finger rhythm. "Then practice stealth walking. We move when the chocolate cake arrives. Sugar comas guarantee a silent exit. Remember, absolutely no balloons. Static electricity ruined Brussels. Understood. I will bring a wagon and earplugs."
created_at
"2026-04-27T10:37:49.48Z"
4/27/2026, 10:37:49 AM
model
"qwen/qwen3.6-max-preview-20260420"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1494
moderation_latency
(null)
generation_time
187023
tokens_prompt
77
tokens_completion
6019
native_tokens_prompt
76
native_tokens_completion
6976
native_tokens_completion_images
(null)
native_tokens_reasoning
6715
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"
usage
0.0545116
router
(null)
provider_responses
0
endpoint_id
"ca7fc0c7-f23d-4ac5-b2e0-945be5b61787"
id
"chatcmpl-13dc2194-0abe-992c-bd81-827f98280fe7"
is_byok
false
latency
1494
model_permaslug
"qwen/qwen3.6-max-preview-20260420"
provider_name
"Alibaba"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777286269-7JhfoK4j55Cx5cs3CxmH"
session_id
(null)
api_type
"completions"
id
"gen-1777286269-cjb65XgdpqD2scVDY6Rr"
upstream_id
"chatcmpl-13dc2194-0abe-992c-bd81-827f98280fe7"
total_cost
0.0545116
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
100.00%
Dialogue to Total Word Ratio
Ratio: 50.00%, Deviation: 0.00%
neededClean
false
wordsTotal
200
wordsDialogue
100
100.0000%