NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ78DVMCANJVHRB7148RJS2Z
Run Details
Model:
Qwen 3.6 Flash
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
51.6s
Cost:
$0.016595
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
95.82%
Dialogue to Total Word Ratio
(details)
47.9105%
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 adjusted her clown nose with trembling fingers. "The laser grid is actually just helium balloons connected to whoopee cushions. You'll trigger a squeak, not an alarm." Bill adjusted his grunting gravity boots. Molly checked her gadget-laden utility belt. Bill stared at the blueprints spread over a sticky picnic table. "So we don't need sonic dampeners?" "We need earplugs. Those whoopee cushions are vicious." Molly slapped a bag of powdered sugar on the table. "This will blind the golden retriever. Code name: Fido." Bill raised an eyebrow. "Last time you underestimated a beast, we lost a pair of tights and my dignity." Bill kicked a pebble toward the inflatable castle, where the muffled bass of 'Baby Shark' thumped through the vinyl walls. Molly poured the sugar into a custom-molded dispersal cannon, her expression grim. "Fido is napping. The party starts at four. We have ninety minutes to swap the gift pile for identical cardboard boxes filled with rocks." "They'll spot the missing tech." "Not if we replace them with slightly used calculators." Molly tapped the blueprints. "The list confirms it." Bill sighed, zipping his stealth suit. "I hate that I believe you. Where are the suitcases?" They waited for the clock to strike three. "In the bouncy castle." "Move fast, Bill. If the magician sees us, he'll put us in a box. It ruins my shoes." Across the lawn, a garden gnome seemed to wink at them, mocking their amateur hour. They had to be ghosts by curtain call. Shoes squeaked.
created_at
"2026-04-27T10:40:42.644Z"
4/27/2026, 10:40:42 AM
model
"qwen/qwen3.6-flash"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
637
moderation_latency
(null)
generation_time
51233
tokens_prompt
77
tokens_completion
9512
native_tokens_prompt
76
native_tokens_completion
11051
native_tokens_completion_images
(null)
native_tokens_reasoning
10702
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
0.0165955
router
(null)
provider_responses
0
endpoint_id
"2435bec9-c808-4f27-9fc8-12f3460d7b66"
id
"chatcmpl-2dca29d1-ad9c-9c10-a283-2dbbd5b13be5"
is_byok
false
latency
637
model_permaslug
"qwen/qwen3.6-flash"
provider_name
"Alibaba"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777286442-IxtedFcLDftaoXPJOPQc"
session_id
(null)
api_type
"completions"
id
"gen-1777286442-k9m5036HUoNhJSDzeib7"
upstream_id
"chatcmpl-2dca29d1-ad9c-9c10-a283-2dbbd5b13be5"
total_cost
0.0165955
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
251
95.82%
Dialogue to Total Word Ratio
Ratio: 54.55%, Deviation: 4.55%
neededClean
false
wordsTotal
253
wordsDialogue
138
47.9105%