NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY7ZXFCCFHKDFVCDPZ1CT6G
Run Details
Model:
Gemma 3 4B
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
3.0s
Cost:
$0.000022
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
60.65%
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 warm bread hung thick in the air, a comforting blanket against the drizzle outside. Flour dusted the counter where a half-finished batch of cranberry scones sat, glistening under the warm glow of the pendant lights. “You’re awfully quiet, Martha,”
a voice said
, low and laced with concern. “Usually, you’re rattling on about Mrs. Higgins’ cat again.” “Just…observing,” came the reply, careful and measured. A delicate hand traced the rim of a chipped mug filled with steaming chamomile tea. “It’s unsettling, isn’t it? How quickly things change.” “Change how?” “Mr. Peterson’s prize-winning pumpkin vanished from his porch last night. Not just gone, *vanished*. And not a trace. The sheriff’s scratching his head, of course.” A small sigh escaped, barely audible above the gentle whir of the mixer. “Well, pumpkins aren’t exactly known for their dramatic escapes. Maybe a deer?” “Deer don’t carry wheelbarrows, Silas.” A pause. “And Peterson swears he heard a car.”
created_at
"2026-02-20T19:21:26.776Z"
2/20/2026, 7:21:26 PM
model
"google/gemma-3-4b-it"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
149
moderation_latency
(null)
generation_time
2855
tokens_prompt
98
tokens_completion
281
native_tokens_prompt
76
native_tokens_completion
241
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
0.00002232
router
(null)
provider_responses
0
endpoint_id
"d3de3bd4-81bc-48fb-924f-2a87b2a36e75"
id
"chatcmpl-RHybl5f389NWNwwiDp54rTex"
is_byok
false
latency
56
model_permaslug
"google/gemma-3-4b-it"
provider_name
"DeepInfra"
status
200
api_type
"completions"
id
"gen-1771615286-WPHXUTLw3a1dShsm5AdG"
upstream_id
"chatcmpl-RHybl5f389NWNwwiDp54rTex"
total_cost
0.00002232
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
60.65%
Count dialogue tags
n/a
neededClean
false
dialogueTags
0
"a voice said"