NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-25-01KMJ8XXM9F4GPBDX09A8SSKJB
Run Details
Model:
Qwen 3 32B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
9.3s
Cost:
$0.000375
Provider:
AtlasCloud
Evaluation summary
Score
Evaluator
Details Link
99.38%
Matches word count
(details)
14.97%
Dialogue to Total Word Ratio
(details)
57.1738%
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
"Are you *nuts*?" Molly hissed, adjusting the tiara on her head. "A children’s party? That’s not a job, that’s suicide." "Suicide for amateurs," Bill said, grinning behind his clown nose. "They won’t expect it. It’s chaotic, festive, full of distractions and glitter." "I'm allergic to glitter," Molly muttered, rolling her eyes. “And balloons.” "Details, details,” Bill waved a plastic sword at her. “We're in plain sight as party entertainers—me with magic tricks, you juggling cupcakes. No one suspects fun. Meanwhile, we slip into the storage room and grab every plush rabbit and Lego set in there." "And what happens when they realize half the presents are missing?" Bill shrugged. “We leave a note: ‘Happy Holidays from the Secret Santa Squirrels.’ They’re kids’ parents. They’ll think it's part of the theme.” “They will *not*. Someone named ‘Santa Squirrel’ isn’t gonna cut it if those parents paid $80 per gift basket!” "You worry too much. We blend in, we steal discreetly, we get paid by the toy truck." Molly sighed. “You’re an idiot.” "But a *successful* one," Bill said happily, twirling a balloon like a baton. "Yes," she said, rubbing her temples. "I can already see the headlines: 'Local Woman Tackled by Six-Year-Old During Toy Caper.'"
created_at
"2026-03-25T10:34:02.253Z"
3/25/2026, 10:34:02 AM
model
"qwen/qwen3-32b-04-28"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
712
moderation_latency
(null)
generation_time
9229
tokens_prompt
93
tokens_completion
350
native_tokens_prompt
76
native_tokens_completion
306
native_tokens_completion_images
(null)
native_tokens_reasoning
0
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.0003748
router
(null)
provider_responses
0
endpoint_id
"2693bf9a-1732-4008-acc9-d241214e936c"
id
"2159978a6a044386afa4e198bc46a17a"
is_byok
false
latency
712
model_permaslug
"qwen/qwen3-32b-04-28"
provider_name
"AtlasCloud"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1774434842-lDtmxsgaOZYJ8yyS6Ok9"
upstream_id
"2159978a6a044386afa4e198bc46a17a"
total_cost
0.0003748
cache_discount
(null)
upstream_inference_cost
0
provider_name
"AtlasCloud"
Evaluation details
Result
Evaluator
Details
Meta Data
99.38%
Matches word count
n/a
neededClean
false
words
205
14.97%
Dialogue to Total Word Ratio
Ratio: 78.26%, Deviation: 11.74%
neededClean
false
wordsTotal
207
wordsDialogue
162
57.1738%