NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY8R17B57V4Y51VBFZVPM87
Run Details
Model:
Gemma 3 12B
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
5.6s
Cost:
$0.000037
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
95.99%
Matches word count
(details)
90.47%
Dialogue to Total Word Ratio
(details)
93.2301%
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 bouncy castle loomed, a garish pink and blue monstrosity dominating the suburban lawn. Streamers drooped like exhausted party favors, and the air shimmered with the sugary scent of melted frosting and desperation. Molly, clutching a pair of binoculars, surveyed the scene with the intensity of a general assessing a battlefield. Bill, meanwhile, was attempting to blend in by mimicking the erratic movements of a five-year-old chasing bubbles. A truly terrifying sight. He tripped over a rogue croquet hoop. "Oof," he mumbled. Molly didn't lower the binoculars. "Graceful, as always." The chaos was glorious. Children, fueled by cake and excitement, were a swirling mass of tiny limbs and shrill laughter. Security, it seemed, consisted of a man in a giant rabbit costume struggling to keep a balloon from flying away. Perfect. The target, a table piled high with brightly wrapped presents, sat directly beneath a banner proclaiming “Lily’s 6th Birthday!” Molly zoomed in. "Look at that," she breathed, "a genuine Thomas the Tank Engine. Our payday just got significantly better.” Bill picked himself up, brushing grass from his increasingly ridiculous Hawaiian shirt. "Right then. Operation Sugar Rush is a go?"
created_at
"2026-02-20T19:34:37.047Z"
2/20/2026, 7:34:37 PM
model
"google/gemma-3-12b-it"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
372
moderation_latency
(null)
generation_time
5505
tokens_prompt
93
tokens_completion
315
native_tokens_prompt
75
native_tokens_completion
261
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
0.00003693
router
(null)
provider_responses
0
endpoint_id
"eb06dc92-5a16-47ec-a776-6ef956457c47"
id
"chatcmpl-RxYswqmvcU8gdpaS3d0YESUt"
is_byok
false
latency
50
model_permaslug
"google/gemma-3-12b-it"
provider_name
"DeepInfra"
status
200
api_type
"completions"
id
"gen-1771616077-JWfoKNR83nz48zLWV7YE"
upstream_id
"chatcmpl-RxYswqmvcU8gdpaS3d0YESUt"
total_cost
0.00003693
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
192
90.47%
Dialogue to Total Word Ratio
Ratio: 15.63%, Deviation: 5.62%
neededClean
false
wordsTotal
192
wordsDialogue
30
93.2301%