NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY81F6DH6HDK6AREC4AQ018
Run Details
Model:
Gemma 3 4B
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
3.2s
Cost:
$0.000025
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 sugar hung thick in the air, battling with the dampness of the morning rain. Flour dusted the worn wooden counter where a half-finished batch of blueberry muffins sat cooling. “You’re awfully quiet, Martha,”
a voice observed
, laced with a gentle amusement. “Just…observing,” came the reply, accompanied by a delicate swirl of frosting onto a cupcake. “Mr. Henderson seems particularly agitated this morning. He’s been pacing by the windows for the last twenty minutes.” “Agitated about what, do you think?” “Honestly? I have no idea. He did spend a good ten minutes staring at Mrs. Gable’s prize-winning roses before he came in. And then he practically demanded a sourdough loaf, which is unusual for him – he usually goes for rye.” A small, knowing smile played on the lips shaping the cupcake. “He’s been having a rather…complicated week, hasn’t he?” “Let’s just say a certain inheritance appears to be causing a considerable amount of distress. And Mrs. Gable’s roses are rather spectacular. Perhaps a little too spectacular for a man wrestling with a will.” “You’re a dreadful gossip, you know that?” “Only when there’s a good story to be had.”
created_at
"2026-02-20T19:22:17.687Z"
2/20/2026, 7:22:17 PM
model
"google/gemma-3-4b-it"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
132
moderation_latency
(null)
generation_time
3045
tokens_prompt
98
tokens_completion
330
native_tokens_prompt
76
native_tokens_completion
279
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
0.00002536
router
(null)
provider_responses
0
endpoint_id
"d3de3bd4-81bc-48fb-924f-2a87b2a36e75"
id
"chatcmpl-RJIjHU4X1S04oJbLVrn1BPmP"
is_byok
false
latency
46
model_permaslug
"google/gemma-3-4b-it"
provider_name
"DeepInfra"
status
200
api_type
"completions"
id
"gen-1771615337-XSBf2JGk0SATxbT9Nj6G"
upstream_id
"chatcmpl-RJIjHU4X1S04oJbLVrn1BPmP"
total_cost
0.00002536
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 observed"