NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHYAK7QTC1QBR9A6WWCTG7SH
Run Details
Model:
Gemma 3 27B
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
5.1s
Cost:
$0.000089
Provider:
Nebius
Evaluation summary
Score
Evaluator
Details Link
43.38%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
21.6892%
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
The inflatable bouncy castle loomed, a garish pink and purple monstrosity dominating Mrs. Higgins’ perfectly manicured garden. Molly squinted, adjusting the ridiculous oversized sunglasses. Bill, meanwhile, was meticulously studying a diagram scrawled on a napkin – a tactical overview of the party’s layout, complete with estimations of juice box consumption and potential Lego-related trip hazards. “Right,” Bill muttered, circling the gift table in red pen. “Maximum security zone. Probably guarded by a six-year-old with a sticky hand.” Molly snorted. She’d handled worse. Like that time with the poodle and the diamond collar. “Focus, Bill. We need a diversion.” He tapped his chin. “Pinata?” “Too obvious. Think… subtle chaos.” Molly spotted a small child attempting to scale the bouncy castle. Inspiration struck. “You handle the emotional support,” she said, already reaching for her pocketful of bubbles. Bill blinked. "Emotional support?" “Just… look concerned while I unleash a bubble storm of epic proportions. It’ll be beautiful. And distracting. They’ll be too busy popping bubbles to notice a couple of present-acquisition specialists.” He sighed. “This is why they don't let me plan anymore."
created_at
"2026-02-20T20:06:57.028Z"
2/20/2026, 8:06:57 PM
model
"google/gemma-3-27b-it"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
296
moderation_latency
(null)
generation_time
4986
tokens_prompt
93
tokens_completion
338
native_tokens_prompt
75
native_tokens_completion
271
native_tokens_completion_images
(null)
native_tokens_reasoning
0
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
0.0000888
router
(null)
provider_responses
0
endpoint_id
"db3af039-8c6e-4b32-bbf5-c858d644d1b5"
id
"chatcmpl-780a28105e24455599678585aa2d2d06"
is_byok
false
latency
296
model_permaslug
"google/gemma-3-27b-it"
provider_name
"Nebius"
status
200
api_type
"completions"
id
"gen-1771618017-uWZAZo4EOxmSgCJpVbfy"
upstream_id
"chatcmpl-780a28105e24455599678585aa2d2d06"
total_cost
0.0000888
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Nebius"
Evaluation details
Result
Evaluator
Details
Meta Data
43.38%
Matches word count
n/a
neededClean
false
words
183
0.00%
Dialogue to Total Word Ratio
Ratio: 42.62%, Deviation: 32.62%
neededClean
false
wordsTotal
183
wordsDialogue
78
21.6892%