NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHYAZXQZ7AGM79MT4MRGB1S7
Run Details
Model:
Gemma 3 4B
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
3.6s
Cost:
$0.000026
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 yeast hung thick in the air, a comforting blanket over "Sugar & Spice." Flour dusted the counter like a fresh snowfall, illuminated by the warm glow of the hanging pendant lights. A half-finished crossword puzzle lay beside a plate of day-old blueberry muffins. “You’re awfully quiet,”
a voice observed
, laced with a subtle note of concern. “Been staring at that puzzle for ten minutes.” “Just trying to distract myself,” came the reply, a small sigh escaping. “It’s… unsettling, isn’t it? The way everything’s shifted.” “Shifted how?” “Old Man Hemlock. Found him this morning. In the gazebo. Rose thorns tangled in his coat. Wasn’t a struggle. Just… still.” A beat of silence, punctuated by the rhythmic thump of the bread mixer. “The sheriff’s been notified, of course.” “Naturally. But Sheriff Brody’s distracted. He’s practically glued to Mrs. Gable’s prize-winning pumpkin patch. Said it’s ‘vital to the town’s morale.’” “Vital to the town’s morale?”
The voice chuckled
, a dry, brittle sound. “That’s a new one.” “Tell me about it. Makes you wonder if the rose thorns were a message of some sort.”
created_at
"2026-02-20T20:13:52.778Z"
2/20/2026, 8:13:52 PM
model
"google/gemma-3-4b-it"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
147
moderation_latency
(null)
generation_time
3429
tokens_prompt
98
tokens_completion
328
native_tokens_prompt
76
native_tokens_completion
289
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
0.00002616
router
(null)
provider_responses
0
endpoint_id
"d3de3bd4-81bc-48fb-924f-2a87b2a36e75"
id
"chatcmpl-Rmpwd3cK1rxzgp85oQTlj6KZ"
is_byok
false
latency
50
model_permaslug
"google/gemma-3-4b-it"
provider_name
"DeepInfra"
status
200
api_type
"completions"
id
"gen-1771618432-pVMixQ2dSZ9WFhFyQqca"
upstream_id
"chatcmpl-Rmpwd3cK1rxzgp85oQTlj6KZ"
total_cost
0.00002616
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 observed"
1
"The voice chuckled"