NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ74DKZFVZTWDR4T7SBEPGYT
Run Details
Model:
Qwen 3.6 35B
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
1m 22s
Cost:
$0.013270
Provider:
AtlasCloud
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.3548%
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 neon tutu, checking the tension on her grappling hook made of twisted licorice. "Bill, focus. The piñata is our distraction. When it breaks, the parents panic. We grab everything." Bill peered through juice-box binoculars. "What are we grabbing? The loot looks heavy." Molly's grip tightened on the licorice hook as a scream erupted from the yard. A toddler toppled a pile of blocks, signaling the start. Bill checked his bubble wand, his eyes darting toward the clown. The screech of tearing cardboard filled the air as the piñata finally surrendered its sugary secrets. "Lego sets, consoles, and the unicorn slide. All of it. I'm the chaotic auntie with zero boundaries." Bill shivered, tightening the straps of his reusable straw fanny pack. "You got banned from yoga for laughing. That persona is dangerous." "Authenticity is key. I oiled the ball pit mesh for the exit. When the cake comes out, we move." Bill gripped his laser pointer. "And the face painter? Remember to grab the dog in the tutu too." Molly smirked, eyeing the backyard like a shark scenting blood. "You handle the painter. I'll take balloons. If I don't return, tell my cat about the tuna too." Bill nodded, swallowing hard nervously outside.
created_at
"2026-04-27T09:30:40.503Z"
4/27/2026, 9:30:40 AM
model
"qwen/qwen3.6-35b-a3b-20260415"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
977
moderation_latency
(null)
generation_time
82091
tokens_prompt
77
tokens_completion
10583
native_tokens_prompt
76
native_tokens_completion
13735
native_tokens_completion_images
(null)
native_tokens_reasoning
13431
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
0.013269959
router
(null)
provider_responses
0
endpoint_id
"179c6985-3a1c-48f1-a009-9f3e3e402cdd"
id
"606ad629e4554d3cb818602b55dadb9a"
is_byok
false
latency
977
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-1777282240-iUk0jZoQx0u7BqqVoTF7"
session_id
(null)
api_type
"completions"
id
"gen-1777282240-13nDJcuE8u9XTJWIAjJY"
upstream_id
"606ad629e4554d3cb818602b55dadb9a"
total_cost
0.013269959
cache_discount
(null)
upstream_inference_cost
0
provider_name
"AtlasCloud"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
98.71%
Matches word count
n/a
neededClean
false
words
206
100.00%
Dialogue to Total Word Ratio
Ratio: 49.28%, Deviation: 0.72%
neededClean
false
wordsTotal
207
wordsDialogue
102
99.3548%