NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-25-01KJ95TVPK5D3PNQEV4B5Q14WS
Run Details
Model:
Gemini 3 Flash (Preview, Reasoning)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
8.9s
Cost:
$0.003814
Provider:
Google AI Studio
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 proofing yeast and burnt sugar hung heavy in the warm air of the Crumb & Whistle. Outside, a persistent drizzle blurred the pastel storefronts of Pebble Creek, turning the cobblestones into dark, slick mirrors. "I’m telling you, it wasn’t on the rack when I turned the ovens on at five." "Are you absolutely certain? It’s a heavy silver ladle, Clara. Hard to misplace between the sink and the stove." "I checked the flour bins, the proofing drawers, and even the industrial freezer. It’s vanished." "And the back door stayed bolted?" "Double-locked from the inside. Just like always. But there was a smudge on the pantry windowsill. A strange, oily residue." "Blue?" "Electric blue. The exact shade of the shutters on the new vicar’s cottage." A tray of almond croissants slid onto the cooling rack with a crisp, metallic clatter. "He’s been in here every morning this week, always asking about the building's history." "He’s a man of the cloth, supposedly. Why would he want an antique soup ladle?" "Maybe it isn't the silver he’s after. My grandmother always said there was a map etched into the handle." "A map to what? The town's original spring?" "Or the vault they walled up during the Great Fire."
created_at
"2026-02-25T01:15:22.712Z"
2/25/2026, 1:15:22 AM
model
"google/gemini-3-flash-preview-20251217"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2012
moderation_latency
(null)
generation_time
8883
tokens_prompt
81
tokens_completion
632
native_tokens_prompt
68
native_tokens_completion
1260
native_tokens_completion_images
0
native_tokens_reasoning
959
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
0.003814
router
(null)
provider_responses
0
endpoint_id
"6e82f652-2693-4b60-bbe0-7362d6e345f0"
is_byok
false
latency
2010
model_permaslug
"google/gemini-3-flash-preview-20251217"
provider_name
"Google AI Studio"
status
200
api_type
"completions"
id
"gen-1771982122-HQb9UIKcgo4xXgmQZAYa"
upstream_id
(null)
total_cost
0.003814
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)