NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-25-01KMJ7VBJQQB7VVEB38P1MYWK5
Run Details
Model:
Qwen 3 32B
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
11.6s
Cost:
$0.000174
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
20.19%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
10.0948%
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 crouched inside the inflatable castle, her neon party hat askew, while Bill fumbled with a sonic lockpick noisier than a toddler’s rattle. Outside, a kazoo parade blared through the park. "You’re supposed to *vibrate* it, not *trombone* it," she hissed, yanking the device from his hand. The lock clattered open. Bill winced. "That was close. What if the piñata saw?" Molly glanced at the sagging fiberglass donkey drooping nearby. "It’s eight pounds of papier-mâché. Unless it’s been secretly training for the Olympics." She slid into the party tent, where glitter-coated gifts glowed under blacklights. Bill followed, tripping over a bounce house moat. "We just need to swap the tags," Molly whispered, plucking a unicorn-wrapped box. "Simple." Bill snorted. "Simple? We’re robbing a place that sells *happiness* as a service!" A sudden crash—a clown cartwheeling into view—sent them flattening against a stack of balloons. "Remember," Molly murmured, "we’re part of the entertainment. Act normal." Bill nodded, holding a stolen inflatable flamingo like a shrapnel shield. "I’m a *very* serious party starter." Outside, parents cheered. Somewhere, a piñata exploded.
created_at
"2026-03-25T10:15:09.659Z"
3/25/2026, 10:15:09 AM
model
"qwen/qwen3-32b-04-28"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
165
moderation_latency
(null)
generation_time
11470
tokens_prompt
93
tokens_completion
665
native_tokens_prompt
73
native_tokens_completion
602
native_tokens_completion_images
(null)
native_tokens_reasoning
361
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
0.0001744
router
(null)
provider_responses
0
endpoint_id
"6b8c829d-3094-45e7-8139-0a67e09060c3"
id
"cmpl-52551e553d4f49dc97b08d8c426355db"
is_byok
false
latency
108
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-1774433709-OlxNSShikwDTofZgB8iv"
upstream_id
"cmpl-52551e553d4f49dc97b08d8c426355db"
total_cost
0.0001744
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
20.19%
Matches word count
n/a
neededClean
false
words
180
0.00%
Dialogue to Total Word Ratio
Ratio: 34.43%, Deviation: 24.43%
neededClean
false
wordsTotal
183
wordsDialogue
63
10.0948%