NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY850MVARGV7S1XHVVW79NG
Run Details
Model:
Gemma 3 12B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
5.5s
Cost:
$0.000035
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
49.9976%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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
“Right, Bill, focus. Operation Sugar Rush is a go. We’re talking bouncy castle, face painting, and a mountain of untouched presents. Think of the resale value!” Molly tapped a frantic rhythm on a napkin covered in scribbled notes. Bill chewed on his thumbnail. “Molly, stealing presents from children? Really? Are we sure this is… dignified?” “Dignified? Bill, we’re thieves! Dignity flew out the window with that diamond necklace we 'borrowed' last Tuesday. Besides, they have *so many* presents. Little Timmy has three remote control cars alone. Three!” “But…the parents. They’ll be heartbroken.” “Heartbroken they bought their kids too much stuff? Please. We’ll be long gone, heading to Cancun. I'm thinking we hit the main gift pile during the magic show. Distraction is key. You’re on balloon duty – make them *extra* loud.” "Balloon duty? I'm afraid of balloons, Molly. They pop." "Then buy some thick ones, Bill! This is for the greater good, and a very sunny beach.”
created_at
"2026-02-20T19:24:13.863Z"
2/20/2026, 7:24:13 PM
model
"google/gemma-3-12b-it"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
479
moderation_latency
(null)
generation_time
5442
tokens_prompt
93
tokens_completion
273
native_tokens_prompt
75
native_tokens_completion
244
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
0.00003472
router
(null)
provider_responses
0
endpoint_id
"eb06dc92-5a16-47ec-a776-6ef956457c47"
id
"chatcmpl-Rf2FymRtbfvUQCsOKK3AWgHZ"
is_byok
false
latency
47
model_permaslug
"google/gemma-3-12b-it"
provider_name
"DeepInfra"
status
200
api_type
"completions"
id
"gen-1771615453-NzYWPPDUaAFI441SWKPc"
upstream_id
"chatcmpl-Rf2FymRtbfvUQCsOKK3AWgHZ"
total_cost
0.00003472
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
157
100.00%
Dialogue to Total Word Ratio
Ratio: 89.17%, Deviation: 0.83%
neededClean
false
wordsTotal
157
wordsDialogue
140
49.9976%