NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-25-01KMJ7S1M9SPDNKC8WGJMGC8RN
Run Details
Model:
Qwen 3 32B
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
7.9s
Cost:
$0.000208
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
95.99%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
97.9933%
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 behind a inflatable dragon, her neon wig slipping over one eye as she signaled to Bill, who was attempting to hotwire the motion sensor on a bouncy castle. “This is *supposed* to be fun, right?” Bill muttered, squinting at the blinking lights like they were a cryptic riddle. Molly elbowed him into silence just as a toddler barreled past, clutching a rainbow Nerf枪 that discharged a squirty sponge. “We’re stealing toys, not joining the damn circus,” she whispered, adjusting her tiara-shaped walkie-talkie. Bill’s plan involved a fog machine and a dozen stolen party horns for cover, though he’d accidentally set off the sprinklers instead, drenching three parents who’d been mid-chant of *Happy Birthday*. Molly used a grappling hook to snatch gift baskets from ceiling rafters while Bill babbled reassurances to a giggling kindergartener who’d mistaken him for Santa’s less-successful cousin. “Left or right?” she asked, balancing on a cake table as confetti cannons erupted. “Left!” Bill yelled, then winced. She kicked the anchor lever, sending a wave of Mylar balloons and stolen LEGO sets tumbling into their duffel bag. As they fled through a piñata-strewn lawn, Molly tossed Bill a noisy party favor. “For the encore.” He facepalmed as it started spinning like a human-sized top.
created_at
"2026-03-25T10:13:53.935Z"
3/25/2026, 10:13:53 AM
model
"qwen/qwen3-32b-04-28"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
106
moderation_latency
(null)
generation_time
7723
tokens_prompt
93
tokens_completion
834
native_tokens_prompt
73
native_tokens_completion
721
native_tokens_completion_images
(null)
native_tokens_reasoning
490
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
0.00020772
router
(null)
provider_responses
0
endpoint_id
"6b8c829d-3094-45e7-8139-0a67e09060c3"
id
"cmpl-c9794510e2a44d228db735701afe80e3"
is_byok
false
latency
56
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-1774433633-BVMCG6EByB4SLS3fNlXq"
upstream_id
"cmpl-c9794510e2a44d228db735701afe80e3"
total_cost
0.00020772
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
95.99%
Matches word count
n/a
neededClean
false
words
208
100.00%
Dialogue to Total Word Ratio
Ratio: 10.28%, Deviation: 0.28%
neededClean
false
wordsTotal
214
wordsDialogue
22
97.9933%