NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ76Y2FMCTDSAHMQPCAP1485
Run Details
Model:
Qwen 3.6 Flash
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
57.3s
Cost:
$0.018006
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
99.98%
Dialogue to Total Word Ratio
(details)
99.9471%
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 traced the grease stains on the pepperoni slices, ignoring the crumb-filled crevices of the blueprint. A crumb dropped onto her boot, mocking their precision. Her clawed glove squeaked against the ventilation grate as she tested the latch mechanism. Her grappling hook tugged impatiently against her hip. "Grid's calibrated for toddlers, Bill. Step easy." Bill sneezed violently, shaking a glitter bomb on his belt until pink sparks showered the floor. "Older kids?" "Check the pressure sensors." Bill squinted at the ventilation shaft, wiping slobber from his chin. "They're set to toddler stomp sensitivity. We're good." "We're wearing squeaky toy suits. The dog will think we're premium playthings. The parents leave at seven for boring toasts. We have a forty-minute window to strip the tree and vanish before cake." "Unicorn?" "Molly, that thing is the size of a Toyota. We leave the unicorn. We take the Lego sets and tablets. Focus! Greed is beautiful, but logistics are better. Do I have to do everything myself?" She tapped her watch with a clawed glove. Bill fumbled for the grappling hook, dropping it on his foot and hissing silently. "Just hand me the grappling hook." "Always. The squirrel looks hungry."
created_at
"2026-04-27T10:14:36.795Z"
4/27/2026, 10:14:36 AM
model
"qwen/qwen3.6-flash"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
617
moderation_latency
(null)
generation_time
57220
tokens_prompt
77
tokens_completion
9826
native_tokens_prompt
76
native_tokens_completion
11991
native_tokens_completion_images
(null)
native_tokens_reasoning
11710
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
0.0180055
router
(null)
provider_responses
0
endpoint_id
"2435bec9-c808-4f27-9fc8-12f3460d7b66"
id
"chatcmpl-e8ea0245-498e-9bdc-98ee-73bec92574fc"
is_byok
false
latency
617
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-1777284876-atllLODqQlxBPtiZ6EcN"
session_id
(null)
api_type
"completions"
id
"gen-1777284876-Tgd63kKwgzm1xRdHRDGm"
upstream_id
"chatcmpl-e8ea0245-498e-9bdc-98ee-73bec92574fc"
total_cost
0.0180055
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.92%
Matches word count
n/a
neededClean
false
words
197
99.98%
Dialogue to Total Word Ratio
Ratio: 51.26%, Deviation: 1.26%
neededClean
false
wordsTotal
199
wordsDialogue
102
99.9471%