NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHYA5ANE11FPKXH8DZ9DRMMD
Run Details
Model:
Gemma 3 12B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
10.3s
Cost:
$0.000039
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
99.98%
Dialogue to Total Word Ratio
(details)
49.9898%
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, let’s go over this one more time,” Molly said, tapping a highlighter against a sketch of a bouncy castle. “Operation Sugar Rush. We’re targeting Penelope Featherstonehaugh’s fifth birthday. Absolute chaos, reportedly.” Bill squinted. “Chaos involving…prescriptions?” “Presents, Bill! Presents! Think of it—train sets, pony figurines, possibly a miniature grand piano. Easily fenceable.” “A grand piano, Molly? For a five-year-old?” “Doesn't matter! Profit is profit. You’re on distraction duty. Bouncy castle. Full throttle. Exaggerated enthusiasm. Make them think you're a very dedicated, if slightly unhinged, uncle.” “Un-hinged is my middle name, Molly. But how do I get *on* the bouncy castle? It’s, you know, bouncy.” “Wedge yourself in! Make it an event! I’ll sweep in, bags at the ready, grabbing as many presents as possible. Timing is paramount. Go, bounce, grab, vanish. Got it?” “Got it. Bounce, grab, vanish. Sounds… exhausting. Are there cake crumbs involved?” “Focus, Bill. Cake is a bonus. Presents are the mission.”
created_at
"2026-02-20T19:59:21.272Z"
2/20/2026, 7:59:21 PM
model
"google/gemma-3-12b-it"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
266
moderation_latency
(null)
generation_time
10250
tokens_prompt
93
tokens_completion
301
native_tokens_prompt
75
native_tokens_completion
276
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
0.00003888
router
(null)
provider_responses
0
endpoint_id
"eb06dc92-5a16-47ec-a776-6ef956457c47"
id
"chatcmpl-RyjbipVEWvaX1YpL0kgvrCdB"
is_byok
false
latency
62
model_permaslug
"google/gemma-3-12b-it"
provider_name
"DeepInfra"
status
200
api_type
"completions"
id
"gen-1771617561-KZad54rE6i9xVcIlJL0t"
upstream_id
"chatcmpl-RyjbipVEWvaX1YpL0kgvrCdB"
total_cost
0.00003888
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
159
99.98%
Dialogue to Total Word Ratio
Ratio: 91.19%, Deviation: 1.19%
neededClean
false
wordsTotal
159
wordsDialogue
145
49.9898%