NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ72P65STBJTPZJ6BJ50BF27
Run Details
Model:
Qwen 3.6 35B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
59.1s
Cost:
$0.007843
Provider:
AtlasCloud
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9920%
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 hissed, "Bill, check the perimeter. Is the mom still distracted by the piƱata?" Bill whispered, "She's got glitter in her hair and a wine stain on her blouse. Distraction confirmed. We have a window of four minutes before the cake cuts." Molly checked, "Four minutes? That's cutting it close. What's the loot distribution?" Bill nodded, "Three large wrapped boxes near the tree, a stack of smaller items under the table, and did you see the drone delivery?" Molly pointed, "The drone? Don't tell me we're up against a Mavic with a gift tag?" Bill sighed, "Worse. It's an RC helicopter with a bag. I've seen you cry over less, Bill." Molly grumbled, "I have not cried. I was allergic to the confetti. How do we breach?" Bill stepped, "I distract the birthday kid with a magic trick, you grab the sack." Molly waited, "My magic trick is pulling a chicken out of a pocket. That kid has seen that routine twice." Bill lunged, "Just go for the legs. Kick the tablecloth. Chaos ensues, we scoop. grab-and-go." "And if the father intervenes?" "You remind him we're the entertainment. Now get in the clown van and stop reading the menu, you're losing time!"
created_at
"2026-04-27T09:00:24.132Z"
4/27/2026, 9:00:24 AM
model
"qwen/qwen3.6-35b-a3b-20260415"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
886
moderation_latency
(null)
generation_time
58947
tokens_prompt
77
tokens_completion
7195
native_tokens_prompt
76
native_tokens_completion
8113
native_tokens_completion_images
(null)
native_tokens_reasoning
7813
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
0.007843324
router
(null)
provider_responses
0
endpoint_id
"179c6985-3a1c-48f1-a009-9f3e3e402cdd"
id
"f5fa4f424b1a4a098ad32de465ce521d"
is_byok
false
latency
886
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-1777280424-wsebaHnglYM0yM1GqvKY"
session_id
(null)
api_type
"completions"
id
"gen-1777280424-1XbXep3Ak8dE1CaZiWF2"
upstream_id
"f5fa4f424b1a4a098ad32de465ce521d"
total_cost
0.007843324
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
100.00%
Dialogue to Total Word Ratio
Ratio: 90.20%, Deviation: 0.20%
neededClean
false
wordsTotal
204
wordsDialogue
184
99.9920%