NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-25-01KMJ7X1KWWH5CV6YDVWYZ2M4X
Run Details
Model:
Qwen 3 32B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
15.7s
Cost:
$0.000349
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0012%
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 adjusted her unicorn horn headpiece, glaring at Bill, who clutched a balloon cat. “We stick to the wall, grab the presents, and vanish,” Molly said. “Vanish? I’ll vanish if a toddler lassos me. What if theyrecognize the evil unicorn?” Bill gestured to her neon-green horn. “They’ll think it’s part of the ‘mystery quest.’ Now, hand me the noise machine.” Bill handed her a pink earmuff set. “These are for *you*? I thought we agreed you’re the quiet one.” “I’m the *distraction*. You’re the getaway balloon artist.” “I can’t fly a balloon animal! Last time I tried, a pigeon out-flew me!” Molly rolled her eyes. “Just herd the kids toward the piñata while I swap the gifts. Use this.” She tossed him a noisemaker. Bill squinted at it. “A kazoo?” “*Disguised* as a kazoo. Crank it if things go south.” He tested it, producing a wheeze. “This’ll drown out a fire alarm.” “Exactly. Now, remember: when the cake comes out, that’s our cue.” Bill fake-saluted. “Yes, Your Horniness.” Molly snatched his balloon cat. “If you’re not the clown, you’re the balloon. Got it?” “Make mine a flamingo. They’re classier when I drop them.” “Just don’t let it go. We need the noise.” A horn blared inside. Molly tugged Bill’s sleeve. “Time. Stay clumsy, not dead.” Bill adjusted his mustache. “What if they ask why we’re here?” “Say you’re from the ‘laugh factory.’ I’ll tell them you’re *required*.” He sighed. “I hate my job.” “Almost done. Then we’ll be rich, and I’ll buy you a real mustache.” The door creaked open. “Rich, huh?” Bill whispered. “What if it’s *too* shiny in there?” “Then you’ll shine right out of there. Now, *smile*.” They tiptoed in.
created_at
"2026-03-25T10:16:04.992Z"
3/25/2026, 10:16:04 AM
model
"qwen/qwen3-32b-04-28"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
97
moderation_latency
(null)
generation_time
15618
tokens_prompt
93
tokens_completion
1328
native_tokens_prompt
73
native_tokens_completion
1227
native_tokens_completion_images
(null)
native_tokens_reasoning
807
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
0.0003494
router
(null)
provider_responses
0
endpoint_id
"6b8c829d-3094-45e7-8139-0a67e09060c3"
id
"cmpl-852a25cc39cf4c969d5241dc6067b1bc"
is_byok
false
latency
42
model_permaslug
"qwen/qwen3-32b-04-28"
provider_name
"DeepInfra"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1774433764-GdDAkC3336tEPEFocESE"
upstream_id
"cmpl-852a25cc39cf4c969d5241dc6067b1bc"
total_cost
0.0003494
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
283
0.00%
Dialogue to Total Word Ratio
Ratio: 71.93%, Deviation: 18.07%
neededClean
false
wordsTotal
285
wordsDialogue
205
0.0012%