NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ77YWWTBGJDZPJ29HW1DZVF
Run Details
Model:
Qwen 3.6 Flash
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
49.6s
Cost:
$0.017667
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9999%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 crouched behind the plastic inflatable castle, adjusting her tactical visor while Bill meticulously counted the remaining party favors. The suburban lawn stretched before them, dotted with discarded juice boxes and the shattered dreams of overstimulated toddlers. He checked his wrist-mounted gadget that somehow doubled as a high-resolution laser pointer. The backyard gate stood unguarded, flanked by a half-deflated dragon and a suspiciously watchful golden retriever. Bill unrolled a grease-stained blueprint of the dining room, tracing a path past the battery-operated train set and toward the towering tree. Molly practiced her stealth crawl, which mostly involved dragging a laundry bag while occasionally catching her toe on a rubber dinosaur. They had studied the target extensively. The wrapping paper alone represented a fortune in glossy regret. A single sheet of foil-lined cardboard promised to fund their retirement in a non-extradition coastline. Bill adjusted his neon wristbands, ensuring they matched the festive theme perfectly. "Remember the contingency plan for the piƱata," he whispered. "Silence the pop music. Secure every single gift bag. Leave the terrible cupcakes." Molly nodded, already measuring the distance to the fireplace. They prepared to become phantom shoppers, ready to turn childhood wonder into liquid assets with absolute precision.
created_at
"2026-04-27T10:32:32.417Z"
4/27/2026, 10:32:32 AM
model
"qwen/qwen3.6-flash"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
647
moderation_latency
(null)
generation_time
49050
tokens_prompt
77
tokens_completion
9256
native_tokens_prompt
76
native_tokens_completion
11765
native_tokens_completion_images
(null)
native_tokens_reasoning
11505
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
0.0176665
router
(null)
provider_responses
0
endpoint_id
"2435bec9-c808-4f27-9fc8-12f3460d7b66"
id
"chatcmpl-5c67eb63-bbe9-95d7-8415-8e40f4eed379"
is_byok
false
latency
647
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-1777285952-XgFprHYl7sQPs8PtqaPH"
session_id
(null)
api_type
"completions"
id
"gen-1777285952-fmUMZvaVUMsGlun4eelj"
upstream_id
"chatcmpl-5c67eb63-bbe9-95d7-8415-8e40f4eed379"
total_cost
0.0176665
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: 9.66%, Deviation: 0.34%
neededClean
false
wordsTotal
207
wordsDialogue
20
99.9999%