NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ76QEJQSP2PXKPR51H7J7H5
Run Details
Model:
Qwen3.6 Max Preview
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
4m 44s
Cost:
$0.081476
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9995%
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 inflatable castle wheezed like a dying accordion while toddlers in paper crowns terrorized the snack table. Molly adjusted her binoculars and studied the gift mountain piled near the bouncy fortress. Bill crouched beside her, wrestling a tangled roll of duct tape and a plastic spider ring he had confiscated from the driveway. They wore matching caterer uniforms stained with imaginary frosting, the perfect camouflage for suburban chaos. Molly traced the patrol routes of exhausted parents carrying juice boxes and stale cake slices. The target remained unguarded, wrapped in shiny paper and guarded only by a drowsy golden retriever wearing a party hat. Bill checked his watch and nodded toward the side gate. Molly tapped her earpiece and whispered the final coordinates. He grunted and adjusted his tool belt. The operation required precision, timing, and a complete disregard for childhood joy. They would slip past the magician, neutralize the pinata, and extract every boxed toy before the birthday song began. Twilight settled very slowly over the lawn chairs. A tired clown honked twice near the brick garage. "Grab the heavy wrapped boxes first," Molly whispered. "What about the noisy musical toys?" Bill asked. "Leave those for the sleepy dog. Move fast."
created_at
"2026-04-27T10:10:59.985Z"
4/27/2026, 10:10:59 AM
model
"qwen/qwen3.6-max-preview-20260420"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1132
moderation_latency
(null)
generation_time
283674
tokens_prompt
77
tokens_completion
8328
native_tokens_prompt
76
native_tokens_completion
10433
native_tokens_completion_images
(null)
native_tokens_reasoning
10177
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
0.0814762
router
(null)
provider_responses
0
endpoint_id
"ca7fc0c7-f23d-4ac5-b2e0-945be5b61787"
id
"chatcmpl-847b3669-ce41-9b0f-8679-0bd46da41f2b"
is_byok
false
latency
1132
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-1777284660-Cxs8YOHXi0ngA4S4mkI8"
session_id
(null)
api_type
"completions"
id
"gen-1777284660-9r4d9bok3qU5OODM7PJF"
upstream_id
"chatcmpl-847b3669-ce41-9b0f-8679-0bd46da41f2b"
total_cost
0.0814762
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
201
100.00%
Dialogue to Total Word Ratio
Ratio: 9.95%, Deviation: 0.05%
neededClean
false
wordsTotal
201
wordsDialogue
20
99.9995%