NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ777PSGGAKHQFBXEKAWHSA1
Run Details
Model:
Qwen3.6 Max Preview
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
1m 21s
Cost:
$0.022095
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
99.74%
Matches word count
(details)
52.04%
Dialogue to Total Word Ratio
(details)
75.8921%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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, check the blueprint," Bill whispered. "It's a bouncy castle layout, Bill. The loot's in the goodie bags near the clown." "The clown? You didn't mention a clown. Clowns have pockets. Unpredictable pockets." "Focus. We go in as entertainment. You're the magician, I'm the assistant who 'accidentally' vanishes with the gift table." "I can't do magic. I have shaky hands." "Perfect. Kids love tragedy. Extraction is behind the piƱata. Once the sugar rush hits, we grab the Lego sets and bolt." "Lego? Molly, we're professionals. We steal diamonds, not plastic bricks that hurt your feet." "Limited edition Star Wars sets? That pile outvalues the Hope Diamond." "Fine. But if a six-year-old tackles me, I'm dropping the swag." "Coward. Target is the birthday boy. He's got a drone in that red box. We swap it for a brick." "A brick? That's cruel." "It's a heist, Bill. Cruelty is part of the package. Now, put on your oversized shoes. We move at cake time." "And Bill? Don't eat the cake. Last job you got frosting on the thermal drill." "That was red velvet! It stains!" "It compromised the drill. Stick to juice boxes. We're ghosts in balloon animals."
created_at
"2026-04-27T10:19:52.503Z"
4/27/2026, 10:19:52 AM
model
"qwen/qwen3.6-max-preview-20260420"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1154
moderation_latency
(null)
generation_time
80970
tokens_prompt
77
tokens_completion
2731
native_tokens_prompt
76
native_tokens_completion
2820
native_tokens_completion_images
(null)
native_tokens_reasoning
2516
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
0.0220948
router
(null)
provider_responses
0
endpoint_id
"ca7fc0c7-f23d-4ac5-b2e0-945be5b61787"
id
"chatcmpl-f820ed57-8c05-9b03-b288-ab3073d309a8"
is_byok
false
latency
1154
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-1777285192-nmKn400jcHXcUkXrdDVU"
session_id
(null)
api_type
"completions"
id
"gen-1777285192-OqJJe9utvT6RIQeZJsfR"
upstream_id
"chatcmpl-f820ed57-8c05-9b03-b288-ab3073d309a8"
total_cost
0.0220948
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.74%
Matches word count
n/a
neededClean
false
words
196
52.04%
Dialogue to Total Word Ratio
Ratio: 98.99%, Deviation: 8.99%
neededClean
false
wordsTotal
198
wordsDialogue
196
75.8921%