NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-25-01KMJ7Y9R4KV57KXNG9TPC229P
Run Details
Model:
Qwen 3 32B
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
3.0s
Cost:
$0.000464
Provider:
Groq
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
80.56%
Dialogue to Total Word Ratio
(details)
40.2823%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 party-hat disguise in the rearview mirror while Bill fidgeted with a whoopee cushion labeled “Operation: Chaos.” “This is a terrible idea,” Bill whispered, eyes locked on the bounce house through the passenger window. “What if they recognize us from the bakery heist?” “They won’t,” Molly said, cracking her knuckles like a cartoon villain. “Kids only remember cake flavors, not faces. Now pass me the glitter bomb.” Bill handed her a balloon animal shaped like a squirrel. “The *glitter bomb* is the whoopee cushion, Molly. You can’t just call a prank gadget ‘glitter bomb’ and expect me to take you seriously.” “Watch me,” Molly said, marching into the backyard where toddlers screamed under a rainbow bounce-house. “We hit the gift table, swap presents for lookalikes, and vanish before the piñatas get popped.” Bill tripped over a garden gnome. “The *lookalikes* are just old socks. What if someone opens a sock instead of a toy?” “Problem solved,” Molly said, tossing him a pair of neon fidget spinners. “Now *you* distract the clown. I’ll handle the stealthy stuff.” “I can’t distract a clown,” Bill whined. “What if he challenges me to a dance-off? I have two left feet!” “Then dance like a deflated balloon,” Molly hissed, already sneaking toward the gift table. Ten minutes later, Molly returned holding a wrapped soccer ball. “We’re out. The clown challenged *you* to a dance-off.” Bill groaned, mid-sentence as a kid handed him a whoopee cushion. “You *said* they only remember cake!” “They remember this,” Molly said, sprinting. “RUN. The piñatas are *awake*.”
created_at
"2026-03-25T10:16:46.089Z"
3/25/2026, 10:16:46 AM
model
"qwen/qwen3-32b-04-28"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
240
moderation_latency
(null)
generation_time
2730
tokens_prompt
93
tokens_completion
868
native_tokens_prompt
72
native_tokens_completion
751
native_tokens_completion_images
(null)
native_tokens_reasoning
411
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
0.00046397
router
(null)
provider_responses
0
endpoint_id
"e74c0abb-6cef-4454-9bf1-d72b44194b6f"
id
"chatcmpl-f4b71fe2-a81e-4165-9701-8dbc54680823"
is_byok
false
latency
236
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-1774433806-YA7pljlD0lZsbE0QFsvd"
upstream_id
"chatcmpl-f4b71fe2-a81e-4165-9701-8dbc54680823"
total_cost
0.00046397
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
259
80.56%
Dialogue to Total Word Ratio
Ratio: 56.82%, Deviation: 6.82%
neededClean
false
wordsTotal
264
wordsDialogue
150
40.2823%