NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ78K0CCEWE9CJWPB3NCRJCC
Run Details
Model:
Qwen3.6 Max Preview
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
3m 29s
Cost:
$0.061454
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 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
The blueprints were actually a crayon drawing of a bouncy castle, but Molly treated it like vault schematics. She smoothed the wrinkled paper across the sticky diner table, tracing a red marker line past the face painting station and directly toward the gift mountain. Bill adjusted his tiny plastic disguise glasses, seriously studying the logistical nightmare of extracting twenty wrapped parcels while avoiding sugar-fueled six-year-olds. He checked his watch, then his empty duffel bag, calculating weight distribution and nap times with mathematical precision. The operation required stealth, timing, and an unprecedented tolerance for balloon animals. Molly tapped the paper, signaling the extraction point near the pizza station. Bill nodded, mentally rehearsing his diversion involving a misplaced magic wand and a very confused entertainer. They were seasoned professionals, albeit criminals currently debating the structural integrity of a piƱata rope. The target was soft, the security was nonexistent, and the loot was mostly plastic. Still, reputation demanded perfection. They packed their black gear, checked their shoelaces, and prepared to infiltrate the most heavily fortified suburban backyard in the county. Victory awaited them. "Grab the big boxes first." "I will distract the magician." "Watch for the sugar crash." "We take the train set."
created_at
"2026-04-27T10:43:31.349Z"
4/27/2026, 10:43:31 AM
model
"qwen/qwen3.6-max-preview-20260420"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1692
moderation_latency
(null)
generation_time
208852
tokens_prompt
77
tokens_completion
6116
native_tokens_prompt
76
native_tokens_completion
7866
native_tokens_completion_images
(null)
native_tokens_reasoning
7605
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
0.0614536
router
(null)
provider_responses
0
endpoint_id
"ca7fc0c7-f23d-4ac5-b2e0-945be5b61787"
id
"chatcmpl-5be00fbe-11b6-9714-95bc-c796976faef8"
is_byok
false
latency
1692
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-1777286611-jaXUeVV5FGHtVIiEOHcz"
session_id
(null)
api_type
"completions"
id
"gen-1777286611-1NySWbtsLfV3Rgeg6vQR"
upstream_id
"chatcmpl-5be00fbe-11b6-9714-95bc-c796976faef8"
total_cost
0.0614536
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: 9.85%, Deviation: 0.15%
neededClean
false
wordsTotal
203
wordsDialogue
20
100.0000%