NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHYAGBYCWHSCCK26Z83THFM2
Run Details
Model:
Gemma 3 4B
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
3.5s
Cost:
$0.000026
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 bell above the door of “Buttercup’s Bliss” jingled a cheerful greeting, quickly swallowed by the comforting aroma of cinnamon and yeast. A dusting of flour coated the counter, reflecting the afternoon sun in a hazy glow. “You’re early,” a voice remarked, a hint of amusement in the tone. “Couldn’t resist,” came the immediate reply. “The apricot scones are calling my name. And frankly, I needed a distraction.” A small, perfectly formed scone was placed before the other person, accompanied by a miniature ramekin of clotted cream and strawberry jam. “Always a good solution. Though I suspect it’s more than just a distraction.” “Don’t start with the detective talk, please,” the response was clipped. “It’s just… Mrs. Hawthorne’s prize winning pumpkin pie vanished last night. Completely gone. And the local gossip is reaching a fever pitch.” “A vanished pie? Seriously?” There was a genuine note of disbelief. “That’s… remarkably inconvenient.” “Inconvenient is an understatement. It’s a town scandal waiting to happen. And frankly, the sheriff seems more concerned with the state of the rose bushes.” A sigh puffed out, followed by a satisfied bite of the scone. “This is remarkably good, by the way. Almost makes me forget about missing baked goods.”
created_at
"2026-02-20T20:05:23.03Z"
2/20/2026, 8:05:23 PM
model
"google/gemma-3-4b-it"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
156
moderation_latency
(null)
generation_time
3376
tokens_prompt
98
tokens_completion
351
native_tokens_prompt
76
native_tokens_completion
290
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
0.00002624
router
(null)
provider_responses
0
endpoint_id
"d3de3bd4-81bc-48fb-924f-2a87b2a36e75"
id
"chatcmpl-RQGC6Uf5wYCGiQ7i3hWRzGjF"
is_byok
false
latency
46
model_permaslug
"google/gemma-3-4b-it"
provider_name
"DeepInfra"
status
200
api_type
"completions"
id
"gen-1771617923-IfcnaOgiWPlPFlKSFQhp"
upstream_id
"chatcmpl-RQGC6Uf5wYCGiQ7i3hWRzGjF"
total_cost
0.00002624
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)