NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-25-01KMJ92Z47KGCVRMRYECVCFVZB
Run Details
Model:
Qwen 3 32B
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
3.1s
Cost:
$0.000587
Provider:
Groq
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0000%
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 adjusted her fake mustache in the van’s rearview mirror, her reflection half-hidden behind a neon "World’s Best Party Planner" banner. Bill, wearing a Santa Claus mask that covered half his face, fidgeted with a contraption of tinsel and wire. “This is either genius or the beginning of our arrests,” Bill said, holding up a glittery “Take Me to Your Leader” balloon. “Or both,” Molly muttered, scanning the backyard through binoculars. A bounce house shaped like a firetruck groaned under the weight of a dozen toddlers. “We stick to the plan: three minutes, no physical contact with the children, and if any of them start singing, we surrender.” Bill tripped over a Christmas light strand, knocking over a stack of paper plate hats. “What if they have security? Like, a real guard?” “They’re hired clowns,” Molly said, unzipping a duffel bag of “equipment”—a whoopee cushion, a fake baby, and a neon “abracadabra” cape. “Worst-case scenario, we become part of the act.” A small child wearing a dinosaur costume waddled past the van, clutching a popsicle. Bill froze. “Relax,” Molly whispered, nudging him. “They’re all extras in this heist movie. Now, pass me the glitter. We’ve got a gift bag to hijack.” Bill obeyed, grinning. “I brought extra wrapping paper. For, uh… wrapping.” Molly raised an eyebrow. “No! For… distractions!” He lobbed a sparkler toward the bounce house. It sputtered harmlessly. The door to the party slid open. A voice called, “Who wants more cotton candy?” Bill swallowed hard. “They’re serving dessert. Should we… join?” Molly groaned. “Bill. The presents. The *money*.” “Money? There’s a piñata over there. Let’s hit it!” A toddler’s giggle echoed. Molly grabbed his arm. “In three, we’re in and out. Ready?” Bill saluted. “Ready. Should we tell them we’re part of the surprise?” “No.” “Too late!” Bill yelled, leaping from the van with a whoop. “I’M THE SURPRISE!” Molly facepalmed as he sprinted toward the piñata, a dozen children screaming. She sighed, adjusted her mustache, and followed.
created_at
"2026-03-25T10:36:47.627Z"
3/25/2026, 10:36:47 AM
model
"qwen/qwen3-32b-04-28"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
231
moderation_latency
(null)
generation_time
2898
tokens_prompt
93
tokens_completion
1091
native_tokens_prompt
72
native_tokens_completion
959
native_tokens_completion_images
(null)
native_tokens_reasoning
496
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
0.00058669
router
(null)
provider_responses
0
endpoint_id
"e74c0abb-6cef-4454-9bf1-d72b44194b6f"
id
"chatcmpl-1782d26e-18d0-4011-b6f4-a7854f992c3f"
is_byok
false
latency
228
model_permaslug
"qwen/qwen3-32b-04-28"
provider_name
"Groq"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1774435007-IxXGVLnaXupcqc8sWcj6"
upstream_id
"chatcmpl-1782d26e-18d0-4011-b6f4-a7854f992c3f"
total_cost
0.00058669
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Groq"
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
331
0.00%
Dialogue to Total Word Ratio
Ratio: 46.08%, Deviation: 36.08%
neededClean
false
wordsTotal
332
wordsDialogue
153
0.0000%