NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ78EY9HWRWX158JSWG03CHH
Run Details
Model:
Qwen3.6 Max Preview
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
3m 16s
Cost:
$0.055806
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
90.48%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
95.2416%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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 carefully smoothed the wrinkled crayon schematic across the extremely sticky kitchen table while adjusting her cheap black leather gloves. "Listen carefully, Bill. We hit the bouncy castle at fourteen hundred hours." "Fourteen hundred? The clown does balloon poodles then." "Exactly. Distraction. While the parents sip cheap wine, we slip past the piƱata." "What about the birthday boy?" "Occupied. I bribed him with extra juice boxes." "Genius. How do we extract the loot?" "Duffel bags disguised as diaper gifts. We grab the wrapped boxes near the cake table." "Even the giant LEGO set?" "Especially the LEGO set. Fences pay triple for unopened plastic bricks." "Security?" "One exhausted grandmother and a golden retriever named Biscuit." "Biscuit took my thumb last Tuesday." "Wear the chainmail glove. Move fast, stay low, and do not touch the fondant." "What if someone sings?" "Hum along. Blend in. We are just two uncles delivering premium wrapping paper." "I hate singing." "You hate poverty more. Check your smoke bombs." "Loaded. Ready when you are, boss." "Then let us crash this party." "Remember, no prints on the goodie bags." "Copied. Bringing the tactical whoopee cushion?" "Deploy it near the pile for acoustic cover." "What about the magician?" "Amateur. His rabbit owes me cash." "Perfect. Calibrating the hook now."
created_at
"2026-04-27T10:41:18.142Z"
4/27/2026, 10:41:18 AM
model
"qwen/qwen3.6-max-preview-20260420"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1151
moderation_latency
(null)
generation_time
195916
tokens_prompt
77
tokens_completion
5811
native_tokens_prompt
76
native_tokens_completion
7142
native_tokens_completion_images
(null)
native_tokens_reasoning
6805
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
0.0558064
router
(null)
provider_responses
0
endpoint_id
"ca7fc0c7-f23d-4ac5-b2e0-945be5b61787"
id
"chatcmpl-7f5cbfe7-c0e7-99b3-afb2-5eab9cdc8fef"
is_byok
false
latency
1151
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-1777286478-8ZOU0etWtLMmlkuIVmkw"
session_id
(null)
api_type
"completions"
id
"gen-1777286478-HpmHgUWOwjQipYMKe68T"
upstream_id
"chatcmpl-7f5cbfe7-c0e7-99b3-afb2-5eab9cdc8fef"
total_cost
0.0558064
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
90.48%
Matches word count
n/a
neededClean
false
words
210
100.00%
Dialogue to Total Word Ratio
Ratio: 90.48%, Deviation: 0.48%
neededClean
false
wordsTotal
210
wordsDialogue
190
95.2416%