NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ73RS2YBKJJV2RG55NVY02V
Run Details
Model:
Qwen 3.6 35B
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
34.3s
Cost:
$0.005227
Provider:
AtlasCloud
Evaluation summary
Score
Evaluator
Details Link
90.48%
Matches word count
(details)
99.98%
Dialogue to Total Word Ratio
(details)
95.2327%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 grease-stained goggles, staring through the kitchen window at the glitter-covered monstrosity unfolding inside. Balloons shaped like llamas bobbed with sinister cheer, while the air reeked of synthetic strawberry frosting and impending doom. Bill clutched a burlap sack embroidered with STUFF MY SHEET in neon thread, his knuckles white as he smeared cake frosting onto his tactical vest. He pointed a trembling finger at the centerpiece cake, which pulsed with ominous red light. Molly checked her wrist-mounted yo-yo launcher, tapping the dial twice to confirm the payload settings. Bill nodded frantically, rehearsing his shuffle-step to bypass the macarena tripwires laid across the entryway. They crouched behind a dumpster overflowing with expired juice boxes, calculating the trajectory of their escape over a wall of aggressive safety netting while monitoring the thermal signature of the guardian dragon mascot. Bill dug into his utility belt, retrieving a canister labeled "Super Soaker: Milquetoast Edition," while Molly calibrated her grappling hook to fire a glitter bomb at the nanny cam perched on the chandelier. They held their breath as the music swelled for musical chairs. "The cake has a laser grid," Bill whispered. "Distraction protocol alpha," Molly hissed. "Wait, is that the piƱata?" Molly asked. "No, it's the drone, you idiot," Bill replied.
created_at
"2026-04-27T09:19:17.605Z"
4/27/2026, 9:19:17 AM
model
"qwen/qwen3.6-35b-a3b-20260415"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
802
moderation_latency
(null)
generation_time
34172
tokens_prompt
77
tokens_completion
5398
native_tokens_prompt
76
native_tokens_completion
5403
native_tokens_completion_images
(null)
native_tokens_reasoning
5105
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
0.005227496
router
(null)
provider_responses
0
endpoint_id
"179c6985-3a1c-48f1-a009-9f3e3e402cdd"
id
"866fb8d76a8041f688930615896f8f0b"
is_byok
false
latency
802
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-1777281557-OZQEVa3DfE8LwCG7G5AV"
session_id
(null)
api_type
"completions"
id
"gen-1777281557-xKevKamTnTaVO11EwHIQ"
upstream_id
"866fb8d76a8041f688930615896f8f0b"
total_cost
0.005227496
cache_discount
(null)
upstream_inference_cost
0
provider_name
"AtlasCloud"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
90.48%
Matches word count
n/a
neededClean
false
words
210
99.98%
Dialogue to Total Word Ratio
Ratio: 11.16%, Deviation: 1.16%
neededClean
false
wordsTotal
215
wordsDialogue
24
95.2327%