NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHYADNWJX2DAZS6DKKMAVE03
Run Details
Model:
Gemma 3 4B
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
2.9s
Cost:
$0.000022
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0000%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% words of dialogue between two thieves named Molly and Bill who are planning to break into a children's party to steal all the presents. Only include the prose of the scene without any markdown or commentary.
Model response
Messages
Meta
AI
“Right, so, the bouncy castle. Logistics are… sticky,” Molly said, meticulously sketching a diagram on a napkin. “Sticky like Grandma’s fruitcake? Because I’m opting out of any involvement with that,” Bill replied, pushing a half-eaten donut around his plate. “We’re after presents, Molly, not geriatric dessert.” “It’s the only access point! Little Timmy’s dad is obsessed with surveillance. We need to bypass it.” “Bypass it with a glitter bomb? Seriously?” “Don’t be ridiculous. A cleverly placed distraction. Perhaps a sudden, dramatic rendition of ‘Twinkle Twinkle Little Star’?” Bill stared at her. “You’re suggesting we interrupt a five-year-old’s birthday party for musical theatrics?” “It’s a *strategic* theatrical distraction! Think of the chaos. The presents! ‘Let it snow, let it snow, let it snow…’” “Just… get the shrink ray. I’m buying a large pepperoni pizza.” “Excellent. Operation ‘Sugar Rush’ is a go.”
created_at
"2026-02-20T20:03:54.906Z"
2/20/2026, 8:03:54 PM
model
"google/gemma-3-4b-it"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
210
moderation_latency
(null)
generation_time
2798
tokens_prompt
93
tokens_completion
274
native_tokens_prompt
75
native_tokens_completion
237
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
0.00002196
router
(null)
provider_responses
0
endpoint_id
"d3de3bd4-81bc-48fb-924f-2a87b2a36e75"
id
"chatcmpl-R0h1huLEDAFLhBV0SdcOWjor"
is_byok
false
latency
97
model_permaslug
"google/gemma-3-4b-it"
provider_name
"DeepInfra"
status
200
api_type
"completions"
id
"gen-1771617834-pN546Y5eIzyOT77pfxO6"
upstream_id
"chatcmpl-R0h1huLEDAFLhBV0SdcOWjor"
total_cost
0.00002196
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
143
0.00%
Dialogue to Total Word Ratio
Ratio: 83.92%, Deviation: 33.92%
neededClean
false
wordsTotal
143
wordsDialogue
120
0.0000%