NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY8ZESFHCD7KQH5AZH2C4BD
Run Details
Model:
Gemma 3 12B
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
7.3s
Cost:
$0.000036
Provider:
DeepInfra
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 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
The community hall reeked of sugar and desperation. Molly tapped a rolled-up blueprint against her chin. “Right, Bill. Operation Sugar Rush commences at precisely 3:17 PM. That’s when the bouncy castle deflates slightly, creating a visual distraction.” Bill, perpetually chewing gum, raised an eyebrow. “A bouncy castle distraction? Seriously? We’re stealing toys, not infiltrating Fort Knox.” “It’s surprisingly effective, Bill! Trust me. Plus, little Timmy Henderson has a Captain Calico action figure. Prime target. Little genius, that boy.” “And what’s my role in this…bouncy castle ballet?” Bill popped his gum. “You’re on teddy bear lookout. Specifically, the limited edition Reginald Bear. Apparently, he’s worth a small fortune on eBay.” Molly unfurled the blueprint further. “Remember, blend in. Smile. Offer juice boxes. Don't make eye contact with Brenda from the PTA. She suspects everything.” Bill sighed dramatically. “Becoming a friendly, juice box-wielding menace is not how I envisioned this afternoon.” “Just think of the Reginald Bear, Bill! Think of the Reginald Bear!”
created_at
"2026-02-20T19:38:40.318Z"
2/20/2026, 7:38:40 PM
model
"google/gemma-3-12b-it"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
158
moderation_latency
(null)
generation_time
7146
tokens_prompt
93
tokens_completion
301
native_tokens_prompt
75
native_tokens_completion
254
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
0.00003602
router
(null)
provider_responses
0
endpoint_id
"eb06dc92-5a16-47ec-a776-6ef956457c47"
id
"chatcmpl-R95sysDO9u93dE83wEdYjo4R"
is_byok
false
latency
62
model_permaslug
"google/gemma-3-12b-it"
provider_name
"DeepInfra"
status
200
api_type
"completions"
id
"gen-1771616320-V1O56bkdNV9L1cKBv1dT"
upstream_id
"chatcmpl-R95sysDO9u93dE83wEdYjo4R"
total_cost
0.00003602
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
163
0.00%
Dialogue to Total Word Ratio
Ratio: 77.91%, Deviation: 27.91%
neededClean
false
wordsTotal
163
wordsDialogue
127
0.0000%