NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-25-01KJ94VH48V4XPGPX27S3GA431
Run Details
Model:
Gemini 3 Flash (Preview, Reasoning)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
15.7s
Cost:
$0.008179
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 cinnamon and yeast hung heavy in the air, clinging to the lace curtains of the Copper Pot Bakery. Beyond the glass display case, two figures leaned over a tray of cooling bear claws, their voices kept low against the steady hum of the industrial ovens. "The almond croissants are five minutes out, so don't you dare look at that clock again." "It’s not the pastries I'm after this morning, and you know it." "If it’s about the zoning board meeting, I already told you I wasn't there. I was waist-deep in sourdough starter." "Then how do you explain your signature on the petition? The one tucked right between the Mayor’s and that shifty taxidermist’s?" "I might have signed a few things while the flour was flying. It was a frantic Tuesday." "It’s a bold move, supporting a bypass that would drive business right away from this very counter." "Perhaps I’m not as worried about foot traffic as I am about who’s been lurking in the alley behind the cooling racks lately." "You saw him too, then?" "I saw a man in a charcoal trench coat carrying a violin case that looked far too heavy for a fiddle." "In Oakhaven? Don't be theatrical. It was likely just the new music teacher." "The new music teacher doesn't wear Italian wingtips that cost more than my industrial oven." "Fair point. Pass me a scone—the blueberry one. It looks like we have a lot of watching to do."
created_at
"2026-02-25T00:58:16.077Z"
2/25/2026, 12:58:16 AM
model
"google/gemini-3-flash-preview-20251217"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1687
moderation_latency
(null)
generation_time
15641
tokens_prompt
81
tokens_completion
1352
native_tokens_prompt
68
native_tokens_completion
2715
native_tokens_completion_images
0
native_tokens_reasoning
2380
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
0.008179
router
(null)
provider_responses
0
endpoint_id
"6e82f652-2693-4b60-bbe0-7362d6e345f0"
is_byok
false
latency
1686
model_permaslug
"google/gemini-3-flash-preview-20251217"
provider_name
"Google AI Studio"
status
200
api_type
"completions"
id
"gen-1771981096-y8KiMEV3TeIRvAtwNAfX"
upstream_id
(null)
total_cost
0.008179
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)