NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY7X4JE4DJY62FHHRAS30VP
Run Details
Model:
Gemma 3 4B
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
3.4s
Cost:
$0.000024
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
13.53%
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 sourdough hung thick in the air, battling with the lingering sweetness of blueberry muffins. A wooden counter separated me from the display case, showcasing rows of perfectly glazed donuts and crusty loaves. Rain hammered against the window of “Millie’s Marvelous Morsels,” blurring the already sleepy street outside. “You’re awfully quiet, Martha,”
a voice said
, low and laced with a familiar amusement. I glanced up from meticulously arranging a plate of raspberry scones. “Just observing. It’s a fascinating tableau, isn’t it? Old Mr. Henderson staring at the lemon tarts like they hold the secrets of the universe.” A chuckle rippled through the small space. “He’s always been a devotee of the citrus. Though, I suspect it’s more about the glaze than the flavor.” “Perhaps,”
I conceded
, carefully placing a dusting of powdered sugar on a scone. “But he does seem preoccupied. And Beatrice Finch was here earlier, arguing with him about…" I hesitated, glancing towards the back room. "...regarding a rather large donation to the historical society.” “Beatrice and a donation, you say? Sounds like someone’s about to have a very public disagreement, and possibly, a very sticky situation.”
created_at
"2026-02-20T19:19:55.734Z"
2/20/2026, 7:19:55 PM
model
"google/gemma-3-4b-it"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
236
moderation_latency
(null)
generation_time
3225
tokens_prompt
98
tokens_completion
331
native_tokens_prompt
76
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
0.0000244
router
(null)
provider_responses
0
endpoint_id
"d3de3bd4-81bc-48fb-924f-2a87b2a36e75"
id
"chatcmpl-RDIAbHlV1AUKrSacHYQxEY08"
is_byok
false
latency
129
model_permaslug
"google/gemma-3-4b-it"
provider_name
"DeepInfra"
status
200
api_type
"completions"
id
"gen-1771615195-xf30AbOdoJx7HhuXGyDu"
upstream_id
"chatcmpl-RDIAbHlV1AUKrSacHYQxEY08"
total_cost
0.0000244
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
13.53%
Count dialogue tags
n/a
neededClean
false
dialogueTags
0
"a voice said"
1
"I conceded"