NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY8HSP9F97NRW35BFFWDAD8
Run Details
Model:
Gemma 3 12B
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
18.5s
Cost:
$0.000036
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
100.00%
Count dialogue tags
(details)
Model input
User/Human
You are an expert novel writer in the cozy mystery genre. Write a scene of about 200 words, with dialogue between two characters. The dialogue should be unattributed, meaning the speaker is not explicitly mentioned. The scene should be set in a small town bakery. Only return the story, nothing else.
Model response
Messages
Meta
AI
The scent of cinnamon and sugar hung thick in the air, a comforting blanket against the November chill. A dusting of flour coated every surface, evidence of a busy morning. “Honestly, Mrs. Higgins nearly fainted when she saw it. Said it was the most dreadful thing she’d ever witnessed in forty years of baking competitions.” A sigh. “Forty years! You’d think she’d be used to a little…unconventionality.” “Unconventional? It was shaped like a gnome, covered in bright blue frosting, and had a single, googly eye glued to its forehead. I mean, really!” "Well, Penelope did always have a flair for the dramatic. You think it was deliberate?” “Deliberate? To sabotage Beatrice’s prize-winning apple pie? Absolutely. Penelope’s been simmering ever since Beatrice won last year. Remember how she swore the judges were bribed?” “Oh, I remember. Said they clearly had a weakness for Beatrice’s crust. Did you tell Sheriff Davies about this…gnome?” “Not yet. Figured it was best to get a second opinion. And maybe sample a gingerbread man or two first.”
created_at
"2026-02-20T19:31:12.723Z"
2/20/2026, 7:31:12 PM
model
"google/gemma-3-12b-it"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
457
moderation_latency
(null)
generation_time
18439
tokens_prompt
98
tokens_completion
291
native_tokens_prompt
76
native_tokens_completion
250
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
0.00003554
router
(null)
provider_responses
0
endpoint_id
"eb06dc92-5a16-47ec-a776-6ef956457c47"
id
"chatcmpl-RhFD4qH5qRQ5nve8AtlecgbU"
is_byok
false
latency
99
model_permaslug
"google/gemma-3-12b-it"
provider_name
"DeepInfra"
status
200
api_type
"completions"
id
"gen-1771615872-vScbzIM31SfUQoKqfn6A"
upstream_id
"chatcmpl-RhFD4qH5qRQ5nve8AtlecgbU"
total_cost
0.00003554
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)