NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ78A6HRW97HCV8Z4AVDSAF4
Run Details
Model:
Qwen3.6 Max Preview
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
2m 21s
Cost:
$0.039091
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
99.74%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
68.2661%
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
"Check the blueprints, Bill. Where's the loot?" "Gift table's adjacent to the bouncy castle. High traffic, low security." "Security? It's a six-year-old's birthday." "Don't underestimate the parents, Molly. I saw a mom with a whistle and a clipboard. She's PTA president. Worse." "Fine. Disguises?" "I'm thinking clowns. Classic. Invisible." "You hate clowns. You cried at the circus." "Professional sacrifice! Plus, the big shoes hide the lockpicks." "And the escape?" "We blend into the piƱata rush. When the candy hits the floor, we grab the Lego Death Star and vanish." "Wait. The mark is a Lego Death Star?" "Four hundred bucks, Mol. Timmy got a pony. We can't lift a pony." "I've got a trailer." "No ponies! Stick to the plan. In as Bozo and Chuckles, out with the bricks." "Juice boxes? I get shaky." "Capri Sun on extraction. Focus! The magician arrives at 1400 hours. That's our window. He pulls quarters, we pull crates." "Rival operative? I want hazard pay." "Just a dad with a wand. Amateurs. Pack the whoopee cushion?" "Naturally. The seltzer smoke screen?" "Loaded. Let's roll. Timmy won't know what hit him." "Fine. But if a kid asks for a balloon dog, you're on your own." "Deal. Now practice your honk."
created_at
"2026-04-27T10:38:42.75Z"
4/27/2026, 10:38:42 AM
model
"qwen/qwen3.6-max-preview-20260420"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1141
moderation_latency
(null)
generation_time
140997
tokens_prompt
77
tokens_completion
4613
native_tokens_prompt
76
native_tokens_completion
4999
native_tokens_completion_images
(null)
native_tokens_reasoning
4650
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
0.039091
router
(null)
provider_responses
0
endpoint_id
"ca7fc0c7-f23d-4ac5-b2e0-945be5b61787"
id
"chatcmpl-c02bac56-770f-987e-bdae-a9542bdd1cd0"
is_byok
false
latency
1141
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-1777286322-y8HCORVuFw4048bJO3Hl"
session_id
(null)
api_type
"completions"
id
"gen-1777286322-6xWx5Jq5Sp2qkD52XMjc"
upstream_id
"chatcmpl-c02bac56-770f-987e-bdae-a9542bdd1cd0"
total_cost
0.039091
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
204
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
206
wordsDialogue
206
68.2661%