NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ729JG0F8QRRTKB7X6JHNXK
Run Details
Model:
Qwen 3.6 27B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
1m 6s
Cost:
$0.017693
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.9995%
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 adjusted her velvet cap in the dim safehouse. Bill spun a multi-tool on his wooden knee while ignoring the dripping faucet. Okay, so the Henderson kid turns seven at three, Molly said. Parents will be drowning in cake smears and chaotic energy. We slip in during the piñata distraction. Piñata at three-thirty, Bill replied. Perfect storm of sugary violence. I’ll disable the smart locks with this spoofing rig. You handle the gift pile. I prefer working quietly, Molly noted. But a mountain of wrapping paper is calling my name. Are we taking the drones? Only the waterproof ones with the propeller guards, Bill confirmed. Leave the stuffed animals. Bad vibes and terrible resale value. What about the cake table? We leave the cake. We take the trunks under the tree. Gold, tablets, and those stupid coding robots. Coding robots are surprisingly liquid on the black market, Bill mused. Just remember the exit strategy. We ride out on the parade float. The very same exact float? Nobody suspects a talking lion is actually two criminals in a fiberglass shell. Do try explaining that to the authorities later. It never does, darling. That’s precisely why we get away completely clean.
created_at
"2026-04-27T08:53:30.76Z"
4/27/2026, 8:53:30 AM
model
"qwen/qwen3.6-27b-20260422"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
672
moderation_latency
(null)
generation_time
65680
tokens_prompt
77
tokens_completion
4379
native_tokens_prompt
76
native_tokens_completion
4902
native_tokens_completion_images
(null)
native_tokens_reasoning
4635
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
0.0176928
router
(null)
provider_responses
0
endpoint_id
"82097366-3a73-4790-ac36-f96ba9f6f577"
id
"chatcmpl-256e4a36-6a16-9a51-80d6-465dcaa75d25"
is_byok
false
latency
672
model_permaslug
"qwen/qwen3.6-27b-20260422"
provider_name
"Alibaba"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777280010-dFTM5eZn5HVdm8Wic3BZ"
session_id
(null)
api_type
"completions"
id
"gen-1777280010-NDV8kXcJQrZjIoPMz0Je"
upstream_id
"chatcmpl-256e4a36-6a16-9a51-80d6-465dcaa75d25"
total_cost
0.0176928
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
199
0.00%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 90.00%
neededClean
false
wordsTotal
200
wordsDialogue
0
49.9995%