NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ73ANHMYQ1BDTAQWCWJ4H8V
Run Details
Model:
Qwen 3.6 35B
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
1m 19s
Cost:
$0.012033
Provider:
AtlasCloud
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
99.86%
Dialogue to Total Word Ratio
(details)
99.9210%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 shower-curtain cloak while Bill nervously calibrated his grappling-hook party blower. The aroma of frosting guided them toward the open backyard window. The sprinklers hissed, threatening to expose their shadowy silhouettes against the inflatable castle. They crept closer, dodging glitter. The toaster oven sparked. They held breath. Bacon lure failed. Dog yawned. Grasping the handle. Now. "Bill, the algorithm says the piƱata drops in twelve minutes. Are the tinfoil hats charged?" "I'm wearing a toaster oven. I'm charged. But the guard dog?" "Irrelevant. We deployed the premium bacon lures. It's currently humping a squeaky toy. Grab the duffel." Bill hesitated, his ear twitching inside the monkey costume. "What if the mom spots us?" "We are the 'Mystery Magician' and his 'Very Real Monkey.' We do not get spotted; we get applause." "I'm not a monkey, Molly. I'm the tactical lead." "Tactical leads wear ears. Move!" Molly kicked the gate, ending in a graceful face-plant into balloons. She scrambled up, eyes widening at the treasure. Bill adjusted his duct-tape mask. "Focus! That's the Lego Death Star. Bill, stop eating the loot. That's poor tradecraft! Grasping the handle! Yes." Bill fumbled the bag, knocking over a box. He froze, cheeks stuffed. "Go."
created_at
"2026-04-27T09:11:35.226Z"
4/27/2026, 9:11:35 AM
model
"qwen/qwen3.6-35b-a3b-20260415"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
814
moderation_latency
(null)
generation_time
78159
tokens_prompt
77
tokens_completion
10612
native_tokens_prompt
76
native_tokens_completion
12454
native_tokens_completion_images
(null)
native_tokens_reasoning
12132
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
0.012033474
router
(null)
provider_responses
0
endpoint_id
"179c6985-3a1c-48f1-a009-9f3e3e402cdd"
id
"006136323b82423fa1f2b9e39f568a0c"
is_byok
false
latency
814
model_permaslug
"qwen/qwen3.6-35b-a3b-20260415"
provider_name
"AtlasCloud"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777281095-eXMvSG4LPCtYsjg4ZTJt"
session_id
(null)
api_type
"completions"
id
"gen-1777281095-dvjpyvajMeRNXlhjLGJY"
upstream_id
"006136323b82423fa1f2b9e39f568a0c"
total_cost
0.012033474
cache_discount
(null)
upstream_inference_cost
0
provider_name
"AtlasCloud"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.98%
Matches word count
n/a
neededClean
false
words
202
99.86%
Dialogue to Total Word Ratio
Ratio: 48.06%, Deviation: 1.94%
neededClean
false
wordsTotal
206
wordsDialogue
99
99.9210%