NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-25-01KMJ91TKVHGZ6VJMS1HNZ1YAA
Run Details
Model:
Qwen 3 32B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
8.9s
Cost:
$0.000384
Provider:
AtlasCloud
Evaluation summary
Score
Evaluator
Details Link
81.27%
Matches word count
(details)
7.78%
Dialogue to Total Word Ratio
(details)
44.5254%
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
"Okay, so the plan is: we walk in like we belong there," Molly whispered, pacing around the kitchen table where she'd sketched out her scheme in colored Sharpie. Bill leaned back against the fridge. "You're proposing we go as what? Parents?” Molly pointed at him with a marker like it was a sword. “No, genius. We’re going as party crashers pretending to be parents.” “Parents who show up late, suspiciously clean, and have a nervous energy that screams ‘criminals in disguise.’” “It’s subtle,” she said. Bill scoffed. “Subtle as a brick through a balloon wall. You know what they’ll do? They’ll hand us snacks, invite us to blow things up, and then—bam—we’re stuck juggling pinwheels until naptime.” Molly smirked. “Exactly. Distracted, happy, defenseless. We swoop in during the loot distribution, toss the presents into duffel bags filled with cotton candy.” “Cotton candy?” Bill raised an eyebrow. “That’s your anti-motion sensor strategy?” “We’re not stealing diamonds, Bill. This is a bounce house full of toys and glitter. One wrong move and we all end up in preschool detention.” Bill sighed. “Let me guess. You've already got fake nametags?” “‘Hi, I'm Mommie Dearest’ and ‘Daddy Long Legs.’ It's all about the branding.” He groaned. “This is going to end up on YouTube.”
created_at
"2026-03-25T10:36:10.239Z"
3/25/2026, 10:36:10 AM
model
"qwen/qwen3-32b-04-28"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
599
moderation_latency
(null)
generation_time
8893
tokens_prompt
93
tokens_completion
368
native_tokens_prompt
76
native_tokens_completion
314
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
0.0003844
router
(null)
provider_responses
0
endpoint_id
"2693bf9a-1732-4008-acc9-d241214e936c"
id
"627db459453f45a6925081c9ba6f74a6"
is_byok
false
latency
599
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-1774434970-isoC7A8RJJKQzeKdol45"
upstream_id
"627db459453f45a6925081c9ba6f74a6"
total_cost
0.0003844
cache_discount
(null)
upstream_inference_cost
0
provider_name
"AtlasCloud"
Evaluation details
Result
Evaluator
Details
Meta Data
81.27%
Matches word count
n/a
neededClean
false
words
212
7.78%
Dialogue to Total Word Ratio
Ratio: 77.36%, Deviation: 12.64%
neededClean
false
wordsTotal
212
wordsDialogue
164
44.5254%