NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY9RWVMS9PN95DT9KV2Y0WW
Run Details
Model:
Gemma 3 12B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
7.8s
Cost:
$0.000038
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
3.62%
Matches word count
(details)
98.27%
Dialogue to Total Word Ratio
(details)
50.9450%
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, so, bouncy castle, face paint, and a frankly concerning amount of glitter,” Molly muttered, circling a map of the park. “You’re sure this is the right party, Bill? It looks… cheerful.” Bill, fiddling with a pair of oversized novelty sunglasses, scoffed. “Cheerful equals distracted, Molly. Distracted equals opportunity. Think of it, a hundred little terrors hopped up on sugar, completely oblivious to the glorious haul of Lego and Paw Patrol figurines we’re about to acquire.” “Glorious? They’re children’s presents, Bill! What are we going to do with fifty My Little Ponies?” “Resell them on eBay, obviously. 'Slightly used, sparkled with joyous abandon!' High demand, I tell you." He tapped the map. "We go in disguised as entertainers. You're the balloon animal artist, I’m the… the guy who pretends to be a pirate and makes kids laugh.” Molly winced. "A pirate? Really?" “It's commitment, Molly! Are you in or are you going to spend the afternoon contemplating the existential dread of plastic ponies?" "Fine, fine. Pirate it is. But if a child cries, I'm blaming you.”
created_at
"2026-02-20T19:52:33.917Z"
2/20/2026, 7:52:33 PM
model
"google/gemma-3-12b-it"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
433
moderation_latency
(null)
generation_time
7759
tokens_prompt
93
tokens_completion
296
native_tokens_prompt
75
native_tokens_completion
267
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
0.00003771
router
(null)
provider_responses
0
endpoint_id
"eb06dc92-5a16-47ec-a776-6ef956457c47"
id
"chatcmpl-RyCX60zdAFNDsZi2HyPJrter"
is_byok
false
latency
57
model_permaslug
"google/gemma-3-12b-it"
provider_name
"DeepInfra"
status
200
api_type
"completions"
id
"gen-1771617153-1cHVPFe925slmg6yAliX"
upstream_id
"chatcmpl-RyCX60zdAFNDsZi2HyPJrter"
total_cost
0.00003771
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
3.62%
Matches word count
n/a
neededClean
false
words
176
98.27%
Dialogue to Total Word Ratio
Ratio: 86.36%, Deviation: 3.64%
neededClean
false
wordsTotal
176
wordsDialogue
152
50.9450%